© 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. 63741
    Prev
    Next
    INDEX
    Explanations

    template, briefs, price, default

    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
     Pixie
    -0.78
    viles
    -0.78
    حت
    -0.69
    Pane
    -0.69
     Velas
    -0.68
    山崎
    -0.68
    zende
    -0.68
    íncia
    -0.67
    menden
    -0.66
     Guten
    -0.66
    POSITIVE LOGITS
     exit
    0.69
    пар
    0.69
    atoma
    0.66
    pertise
    0.66
    sient
    0.64
     Có
    0.63
    erex
    0.63
     Иван
    0.63
    ordano
    0.63
     fp
    0.62
    Activations Density 0.046%

    No Known Activations