© 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. 73589
    Prev
    Next
    INDEX
    Explanations

    Henri names and São Paulo

    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
    e
    -2.83
    0
    -2.69
    am
    -2.66
    m
    -2.61
     после
    -2.61
     примерно
    -2.55
    b
    -2.55
    _
    -2.45
    c
    -2.39
    A
    -2.34
    POSITIVE LOGITS
    ’
    3.63
     guaranteeing
    2.72
     باسلام
    2.53
    悛
    2.48
    ౭
    2.47
     regula
    2.45
    ⟣
    2.44
    聼
    2.42
    鴴
    2.39
    の作品
    2.38
    Activations Density 0.009%

    No Known Activations