© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64989
    Prev
    Next
    INDEX
    Explanations

    legal and technical documentation

    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
    Ь
    -0.73
    дравству
    -0.68
    erview
    -0.68
    ív
    -0.67
    gotta
    -0.64
     bursa
    -0.64
    Tire
    -0.63
    wheres
    -0.62
     EVE
    -0.62
    ifolia
    -0.62
    POSITIVE LOGITS
    cznego
    0.80
    auc
    0.70
    rw
    0.69
     εφαρ
    0.68
     番
    0.67
     profane
    0.67
    arabe
    0.66
    itur
    0.64
    ENDAR
    0.64
     thuyền
    0.63
    Activations Density 0.082%

    No Known Activations