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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54214
    Prev
    Next
    INDEX
    Explanations

    mail address

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

    The neuron fires on tokens that are code identifiers or symbols written in capital or mixed‐case (e.g. type, module, or constant names) rather than ordinary keywords or punctuation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    новая
    -0.82
    新生
    -0.79
     проми
    -0.78
     correndo
    -0.77
    包
    -0.74
    酪
    -0.74
     Comunicación
    -0.73
    мен
    -0.73
    з
    -0.73
    zelfde
    -0.72
    POSITIVE LOGITS
     again
    0.90
    Mô
    0.87
     опять
    0.85
    Недо
    0.84
    melde
    0.84
    :✨
    0.82
    ykjav
    0.82
     wichtigsten
    0.82
    Verbindung
    0.79
    舺
    0.78
    Activations Density 0.027%

    No Known Activations