© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 80752
    Prev
    Next
    INDEX
    Explanations

    License distributed software

    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
     Laine
    -0.73
    Auteur
    -0.70
    Compound
    -0.70
     optik
    -0.69
     Hatt
    -0.69
    sez
    -0.68
    ⣴
    -0.68
    ोल
    -0.68
    ibli
    -0.68
    dient
    -0.66
    POSITIVE LOGITS
     farben
    0.68
    нта
    0.68
     july
    0.67
     called
    0.63
     JULY
    0.63
    Sma
    0.62
    shiro
    0.61
    Ngo
    0.61
    LAG
    0.60
    gover
    0.60
    Activations Density 0.070%

    No Known Activations