© 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. 63302
    Prev
    Next
    INDEX
    Explanations

    names starting with "jaw" or "kaw" or "maw" or "paw" or "baw"

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

    The neuron is activated by substrings of proper names (i.e. by parts of people’s or places’ names).

    oai_token-act-pair · o4-miniTriggered 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
     juguete
    -0.77
     spół
    -0.77
     Những
    -0.76
     Aktual
    -0.76
     debts
    -0.75
    izar
    -0.74
    Кре
    -0.74
     miłości
    -0.73
    omorphic
    -0.73
    Não
    -0.73
    POSITIVE LOGITS
     maw
    0.94
    raw
    0.89
     Maw
    0.88
    maw
    0.86
     baw
    0.84
     Paw
    0.81
    esome
    0.79
    Paw
    0.79
    Auszeichnungen
    0.79
    T
    0.78
    Activations Density 0.031%

    No Known Activations