© 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. 34-GEMMASCOPE-RES-131K
    7. 1922
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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_34/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
    ist
    -0.85
    idad
    -0.82
    dade
    -0.78
    ij
    -0.78
    ್ಯ
    -0.77
    imento
    -0.77
     current
    -0.76
    尔
    -0.73
    ะ
    -0.73
    ançon
    -0.72
    POSITIVE LOGITS
     centru
    0.75
    ♟
    0.74
    却
    0.74
     tudo
    0.72
    claw
    0.72
     łatwo
    0.72
    ایل
    0.71
    tvar
    0.71
    特殊
    0.70
    alo
    0.69
    Activations Density 0.092%

    No Known Activations