© 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. 72903
    Prev
    Next
    INDEX
    Explanations

    explaining asking or clarifying meaning

    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
    methoden
    -0.91
    ㄉ
    -0.90
     وفا
    -0.88
     vocale
    -0.88
    formatie
    -0.88
     идеи
    -0.88
     pedro
    -0.87
    approximately
    -0.87
    Bibliographie
    -0.85
     kommenden
    -0.85
    POSITIVE LOGITS
     a
    1.26
     basically
    1.07
    .‏
    1.05
     an
    1.02
     another
    1.00
    . 
    0.98
     sekaligus
    0.98
    Personensuche
    0.96
     that
    0.95
    ],
    0.95
    Activations Density 0.053%

    No Known Activations