© 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. 78784
    Prev
    Next
    INDEX
    Explanations

    international punctuation code symbols

    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
     Peirce
    -0.69
     HF
    -0.67
    Ligações
    -0.66
    $__
    -0.66
    ragend
    -0.66
     patterns
    -0.65
    rowad
    -0.64
    patterns
    -0.63
    prefer
    -0.63
     Patterns
    -0.63
    POSITIVE LOGITS
    CRT
    0.82
    とし
    0.73
    ₹
    0.72
     القدر
    0.71
    christ
    0.71
     зрения
    0.69
     другая
    0.69
    iration
    0.68
    RAI
    0.68
    antos
    0.67
    Activations Density 0.054%

    No Known Activations