© 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. 66037
    Prev
    Next
    INDEX
    Explanations

    HTML document metadata

    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
     by
    -1.38
     more
    -1.20
     small
    -1.10
     most
    -1.09
     new
    -1.08
    ↵↵
    -1.06
     long
    -1.04
     start
    -1.03
    SMALL
    -1.02
     even
    -1.00
    POSITIVE LOGITS
    とはいえ
    1.13
     ,‬
    1.05
     Dinas
    1.05
     riduzione
    1.04
    首先
    1.04
     ſy
    1.03
    تها
    1.02
    比如说
    1.02
     ſol
    0.98
     firs
    0.97
    Activations Density 0.032%

    No Known Activations