© 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. 10-GEMMASCOPE-RES-131K
    7. 72684
    Prev
    Next
    INDEX
    Explanations

    cognition

    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_10/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
     We
    -1.91
    ).
    -1.74
    >
    -1.71
    ');
    -1.70
     großes
    -1.64
    涐
    -1.53
     parachoque
    -1.53
    ')
    -1.52
    ;
    -1.52
    If
    -1.49
    POSITIVE LOGITS
     it
    1.77
    новение
    1.66
     aplicable
    1.59
     utiliza
    1.55
    厮
    1.53
     \[
    1.52
    喺
    1.52
    ꔹ
    1.51
     ваша
    1.50
     apporter
    1.49
    Activations Density 0.003%

    No Known Activations