© 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. 73082
    Prev
    Next
    INDEX
    Explanations

    lists specific terms or phrases

    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
     in
    -2.14
     Each
    -1.90
     on
    -1.77
     has
    -1.70
     all
    -1.59
     如果
    -1.58
     Taking
    -1.56
     At
    -1.55
     Would
    -1.54
     time
    -1.47
    POSITIVE LOGITS
    ebly
    1.76
    <bos>
    1.68
     pè
    1.59
    ateness
    1.52
    dienne
    1.52
    酲
    1.51
    vernment
    1.51
     sre
    1.49
     tè
    1.48
    eneral
    1.46
    Activations Density 0.000%

    No Known Activations