© 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. 59417
    Prev
    Next
    INDEX
    Explanations

    sense of

    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
    ?”
    -2.81
    蜴
    -2.72
     estremamente
    -2.63
    栳
    -2.61
     falschen
    -2.56
     erfolgreichen
    -2.55
     mainstay
    -2.53
    
    -2.53
     conocía
    -2.52
    烔
    -2.48
    POSITIVE LOGITS
    providedIn
    2.94
    weakSelf
    2.55
    $
    2.48
    ↵↵
    2.31
     endforeach
    2.30
    </h2>
    2.25
     пр
    2.22
    U
    2.20
    aticano
    2.17
    ),
    2.14
    Activations Density 0.016%

    No Known Activations