© 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. 160672
    Prev
    Next
    INDEX
    Explanations

    help to nourish

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

    muscle breakdown recovery

    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
     編
    0.48
    herjee
    0.47
     Tân
    0.46
     adopté
    0.45
     উন্নয়ন
    0.45
     subsistence
    0.45
     রাজনীতি
    0.45
     स्वतंत्रता
    0.44
     ম্যাজিস্ট্রেট
    0.44
     पहाड़ों
    0.43
    POSITIVE LOGITS
    ቐ
    0.47
    ts
    0.45
    டுக
    0.44
    t
    0.44
    ަނ
    0.43
    Clk
    0.43
     Uhr
    0.42
    чна
    0.42
    s
    0.42
    Ung
    0.42
    Activations Density 0.000%

    No Known Activations