© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 148753
    Prev
    Next
    INDEX
    Explanations

    birth details and locations

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

    encyclopedia entries

    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
     배우
    0.46
     பெயரை
    0.46
    Анд
    0.44
     Surgeons
    0.44
    Artículo
    0.43
    没了
    0.43
    녜
    0.43
    Nun
    0.42
    수에
    0.41
    ₂(
    0.41
    POSITIVE LOGITS
     قبول
    0.52
     tools
    0.46
     ஏற்றுக்கொள்ள
    0.43
     গ্রহণযোগ্য
    0.42
     loopholes
    0.42
     governing
    0.41
     obfusc
    0.41
     outils
    0.41
     pneum
    0.40
     evac
    0.39
    Activations Density 0.005%

    No Known Activations