© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 191784
    Prev
    Next
    INDEX
    Explanations

    common phrases and follow-ups

    np_acts-logits-general · gemini-2.5-flash-lite

    reduced pricing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zhi
    0.52
    z
    0.50
    kys
    0.50
     Boris
    0.50
    inati
    0.49
    ks
    0.49
    kv
    0.48
     Pell
    0.48
    સભા
    0.48
     Seç
    0.48
    POSITIVE LOGITS
    Dated
    0.47
    ляє
    0.43
    প্রণ
    0.42
    uticas
    0.42
     spann
    0.41
     expertly
    0.41
    -\{
    0.40
    owaną
    0.40
    িতেছে
    0.40
     logiciels
    0.39
    Activations Density 0.000%

    No Known Activations