© 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. 30773
    Prev
    Next
    INDEX
    Explanations

    syllables and suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    CharCode
    -0.81
    לם
    -0.76
    Bland
    -0.72
    ❲
    -0.72
    бовать
    -0.71
     représ
    -0.71
    ularia
    -0.70
     balan
    -0.70
    द्र
    -0.70
     PUSH
    -0.69
    POSITIVE LOGITS
    替
    0.78
    ToMap
    0.76
    sertation
    0.73
     upgrades
    0.71
    靖
    0.69
     Cairns
    0.67
     Curious
    0.67
    Tính
    0.66
    onnes
    0.66
    비
    0.66
    Activations Density 0.034%

    No Known Activations