© 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. 145871
    Prev
    Next
    INDEX
    Explanations

    lists by category

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

    Why questions and distinguishing

    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
    н
    0.56
    ن
    0.50
    خط
    0.46
    n
    0.46
    сім
    0.45
     impacts
    0.45
    स्फ
    0.45
    ﻛ
    0.44
     общей
    0.44
    Ḫ
    0.43
    POSITIVE LOGITS
     還
    0.52
     ទ
    0.48
     alami
    0.47
    igungen
    0.47
    鬧
    0.46
     యూ
    0.45
     hoti
    0.45
     មាន
    0.45
     យើង
    0.45
     alamy
    0.44
    Activations Density 0.002%

    No Known Activations