© 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. 57649
    Prev
    Next
    INDEX
    Explanations

    C++ include import

    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
     spirituale
    -0.72
     parlé
    -0.70
     Jordi
    -0.70
    éhez
    -0.69
    lassi
    -0.69
    おきます
    -0.67
    unger
    -0.66
    因子
    -0.65
    FileInfo
    -0.64
    (:,
    -0.63
    POSITIVE LOGITS
     Utama
    0.78
     symmetries
    0.75
    ฒ
    0.75
    posta
    0.70
     ハン
    0.69
     NWS
    0.68
    寸
    0.66
     terrorism
    0.66
    ymmetric
    0.66
    })}
    0.66
    Activations Density 0.050%

    No Known Activations