© 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. 128632
    Prev
    Next
    INDEX
    Explanations

    data encoding and stream operations

    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
    是
    -1.05
     either
    -1.05
    あー
    -1.04
     zákaz
    -1.02
    );
    -0.95
     différents
    -0.94
     generó
    -0.94
     said
    -0.94
    ほら
    -0.94
    信息
    -0.92
    POSITIVE LOGITS
    <bos>
    1.26
     linkovi
    1.19
    曲は
    1.09
     porcent
    1.02
    donde
    1.01
    Morfologia
    0.98
     kohdetta
    0.97
     otros
    0.97
     слегка
    0.97
    Vá
    0.95
    Activations Density 0.002%

    No Known Activations