© 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. 34309
    Prev
    Next
    INDEX
    Explanations

    roles and actions

    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
    ❢
    -1.47
    さぁ
    -1.39
    にほんブログ村
    -1.38
    颚
    -1.38
    ＊＊＊＊
    -1.37
     Ә
    -1.36
     短发
    -1.34
    ❔
    -1.33
     which
    -1.31
    哐
    -1.29
    POSITIVE LOGITS
     finally
    1.89
     to
    1.78
     not
    1.68
     instig
    1.59
     latest
    1.53
     still
    1.48
    が
    1.43
    だけど
    1.41
    もある
    1.40
    など
    1.39
    Activations Density 0.046%

    No Known Activations