© 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. 34104
    Prev
    Next
    INDEX
    Explanations

    parallel async

    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
    簓
    -1.79
    쐈
    -1.77
     régal
    -1.77
    ところに
    -1.73
     célè
    -1.70
     QUÉ
    -1.66
    来週
    -1.63
     první
    -1.62
    んだよね
    -1.62
     estadounid
    -1.59
    POSITIVE LOGITS
     also
    1.98
     in
    1.98
     with
    1.94
     at
    1.94
    が
    1.66
     for
    1.63
    z
    1.57
     on
    1.53
     only
    1.52
    これも
    1.51
    Activations Density 0.002%

    No Known Activations