© 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. 48451
    Prev
    Next
    INDEX
    Explanations

    listing of; super senior; Q:; Manhattan Airport

    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
     if
    -0.88
     продукции
    -0.88
    Ē
    -0.83
    kwds
    -0.83
    君は
    -0.81
     linguistique
    -0.79
     Punj
    -0.77
     проблеми
    -0.76
     EINVAL
    -0.76
     рыбы
    -0.76
    POSITIVE LOGITS
    ragma
    0.99
    TEMA
    0.88
    orescence
    0.87
    spes
    0.86
     vantaggio
    0.86
    EDWARD
    0.86
    𝐯
    0.85
    シック
    0.84
    '])
    0.83
    "])
    0.83
    Activations Density 0.000%

    No Known Activations