© 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. 77859
    Prev
    Next
    INDEX
    Explanations

    programming code, scientific notation, languages

    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
    ఐ
    -0.71
    District
    -0.69
    volles
    -0.67
    INSTALL
    -0.66
     bedenken
    -0.66
     آور
    -0.65
     District
    -0.63
     Galileo
    -0.63
    歳の
    -0.62
    ツ
    -0.62
    POSITIVE LOGITS
    Ple
    0.74
     Ple
    0.74
    льтра
    0.70
    ULUS
    0.69
     nascimento
    0.68
    נם
    0.68
    bris
    0.68
    роди
    0.67
     deliberation
    0.67
    ANIUM
    0.66
    Activations Density 0.043%

    No Known Activations