© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 28327
    Prev
    Next
    INDEX
    Explanations

    products and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    1.08
    IA
    0.84
     be
    0.81
    LE
    0.81
    .
    0.81
    로
    0.76
    ED
    0.75
     diminu
    0.73
    ク
    0.72
     ولی
    0.69
    POSITIVE LOGITS
    ש
    0.95
    t
    0.93
    st
    0.84
    r
    0.83
    دن
    0.82
    sons
    0.82
    en
    0.81
    tà
    0.80
    sale
    0.80
    il
    0.79
    Activations Density 0.038%

    No Known Activations