© 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. 64255
    Prev
    Next
    INDEX
    Explanations

    prefix or start of codes

    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
    Gy
    -0.93
    enoord
    -0.83
    irmer
    -0.82
    gebob
    -0.82
     MacGregor
    -0.78
    اگر
    -0.77
    十足
    -0.77
    Сло
    -0.77
    zs
    -0.77
    FF
    -0.77
    POSITIVE LOGITS
     misterio
    0.85
    мети
    0.83
    🪒
    0.77
    yargs
    0.77
     skills
    0.75
    createNewFile
    0.73
    matte
    0.73
    spine
    0.72
    guna
    0.72
    premiere
    0.72
    Activations Density 0.000%

    No Known Activations