© 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. 22110
    Prev
    Next
    INDEX
    Explanations

    the word bad

    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
     and
    -2.16
    诸多
    -1.82
    Ꮉ
    -1.77
    噥
    -1.72
     Unterneh
    -1.70
     burbu
    -1.70
     kontinu
    -1.64
     bileklik
    -1.63
    ꙳
    -1.60
    
    -1.59
    POSITIVE LOGITS
    あります
    1.99
     also
    1.91
    ".
    1.75
    ."
    1.68
    ",
    1.61
     непло
    1.50
    ).
    1.48
    )
    1.48
     tampoco
    1.46
    蹬
    1.45
    Activations Density 0.003%

    No Known Activations