© 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. 63952
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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
    ítő
    -1.04
    meniz
    -1.01
     then
    -1.00
    רק
    -0.95
     Propriété
    -0.93
     Visibility
    -0.91
    ,(
    -0.91
     diseños
    -0.90
     macetas
    -0.89
    Կ
    -0.88
    POSITIVE LOGITS
     restante
    1.02
    Boxscore
    1.01
     both
    0.96
    Доброго
    0.93
     detailed
    0.93
    ]?.
    0.92
    适当
    0.92
     their
    0.91
    supposed
    0.91
     what
    0.90
    Activations Density 0.044%

    No Known Activations