© 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. 2505
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    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
    говор
    -0.72
    british
    -0.72
     tacos
    -0.71
     Batal
    -0.71
     !-
    -0.71
     zna
    -0.68
    流动
    -0.68
     lebaran
    -0.67
     having
    -0.67
    riors
    -0.67
    POSITIVE LOGITS
     оба
    0.78
    JJ
    0.76
    JF
    0.74
    èze
    0.74
    setz
    0.72
    blé
    0.72
    CR
    0.71
     Tarn
    0.71
    druck
    0.69
    KF
    0.69
    Activations Density 0.025%

    No Known Activations