© 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. 47758
    Prev
    Next
    INDEX
    Explanations

    code keywords and data transformation

    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
     valde
    -0.83
     nuclé
    -0.82
    ここは
    -0.80
     Harz
    -0.80
    OTROS
    -0.79
     maternidade
    -0.79
     superare
    -0.79
    ブログ村
    -0.78
    ここで
    -0.78
    ハナ
    -0.78
    POSITIVE LOGITS
     from
    1.88
     to
    1.84
     транспорт
    0.90
     entity
    0.90
     To
    0.90
    ccccccc
    0.88
    fficiency
    0.87
     إلى
    0.86
     unto
    0.86
     From
    0.85
    Activations Density 0.005%

    No Known Activations