© 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. 21915
    Prev
    Next
    INDEX
    Explanations

    attributing blame to entities

    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
    盌
    -2.75
     This
    -2.50
     शुर
    -2.45
    って思
    -2.42
    }$,
    -2.42
     ktorí
    -2.41
    膑
    -2.39
    婚礼
    -2.38
    後半
    -2.38
     überprü
    -2.38
    POSITIVE LOGITS
    ↵
    3.30
    by
    2.69
    at
    2.63
    un
    2.58
    up
    2.55
    “
    2.41
    ſſel
    2.41
    aw
    2.27
    1
    2.27
    in
    2.25
    Activations Density 0.004%

    No Known Activations