© 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. 191895
    Prev
    Next
    INDEX
    Explanations

    dates, events, and places

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

    words or phrases followed by colons

    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
     Operational
    0.49
    Concept
    0.49
    a
    0.49
    operational
    0.48
     Concept
    0.48
    গঞ্জ
    0.48
    concept
    0.48
    Ĕ
    0.46
    ه
    0.45
    Как
    0.45
    POSITIVE LOGITS
     vant
    0.43
     说明
    0.42
     unsuitable
    0.42
     ثقاف
    0.42
     المال
    0.42
     annuities
    0.41
     vinos
    0.41
    yaj
    0.41
    knię
    0.40
     انسانی
    0.40
    Activations Density 0.001%

    No Known Activations