© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117226
    Prev
    Next
    INDEX
    Explanations

    names starting with Ab

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on capitalized name tokens beginning with the letters “Abb” (e.g. Abbott, Abbas, Abbe, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the character sequence "Abb" or "Aba", typically as part of proper names or technical terms.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    proper nouns containing the “Abb-/Aba-” stem (e.g., names and places starting with that prefix).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     insertar
    -0.83
    搞笑
    -0.77
    dits
    -0.76
    feste
    -0.74
    Tay
    -0.74
     Assault
    -0.73
    jaa
    -0.73
    EOD
    -0.72
    intendo
    -0.71
     あっ
    -0.70
    POSITIVE LOGITS
     picking
    0.77
     mildly
    0.73
    Maybe
    0.72
    стма
    0.71
    ÍA
    0.71
     attention
    0.71
     exiled
    0.70
     plas
    0.70
    Ngày
    0.69
     Oliva
    0.67
    Activations Density 0.033%

    No Known Activations