© 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-262K
    7. 70971
    Prev
    Next
    INDEX
    Explanations

    high concentration to low

    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_262k_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
     famously
    0.50
    र
    0.48
    大力
    0.46
    आई
    0.45
    ЕР
    0.45
     in
    0.44
    īng
    0.44
    ड
    0.43
    е
    0.43
     can
    0.42
    POSITIVE LOGITS
    渦
    0.46
    million
    0.44
     میلیون
    0.43
     limo
    0.43
    slime
    0.43
     slime
    0.42
     جاتی
    0.42
    🍓
    0.42
    کرات
    0.42
    ToEnd
    0.41
    Activations Density 0.005%

    No Known Activations