© 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. 22-GEMMASCOPE-RES-131K
    7. 25393
    Prev
    Next
    INDEX
    Explanations

    java generic types

    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_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
     for
    -1.47
     your
    -1.02
    져
    -1.01
    🇪
    -1.01
     of
    -0.99
     如果
    -0.96
     or
    -0.94
    <h1>
    -0.94
    集合
    -0.93
     from
    -0.91
    POSITIVE LOGITS
    开学
    1.19
    举动
    1.11
    Приготовление
    1.10
     Unterscheidung
    1.05
    tiven
    1.04
    投稿日
    1.02
    そういった
    1.02
    顺便
    1.02
    <bos>
    1.02
    这也
    1.02
    Activations Density 0.009%

    No Known Activations