© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40514
    Prev
    Next
    INDEX
    Explanations

    place and direction

    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
     enviados
    -2.00
     activos
    -1.80
    鉏
    -1.73
    
    -1.71
     Répondre
    -1.71
    齶
    -1.70
     maniere
    -1.68
    峮
    -1.66
    𓆏
    -1.65
    ];
    -1.63
    POSITIVE LOGITS
    in
    2.02
    :
    1.85
    ff
    1.81
    la
    1.74
    of
    1.72
    by
    1.72
    -
    1.72
    kk
    1.70
    one
    1.69
     for
    1.65
    Activations Density 0.023%

    No Known Activations