© 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. 58199
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers and binary representations

    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
    いけない
    -0.84
     million
    -0.82
    ্ষ
    -0.79
     and
    -0.79
     milyon
    -0.78
    ならば
    -0.77
    كاتب
    -0.76
     millions
    -0.75
     existen
    -0.75
     personally
    -0.74
    POSITIVE LOGITS
    nowa
    0.94
     pediat
    0.93
     SAME
    0.91
    ঢ
    0.88
    δη
    0.88
     ""],
    0.88
    ordenadas
    0.87
    uremberg
    0.86
    ۰۰
    0.86
    ⋁
    0.86
    Activations Density 0.018%

    No Known Activations