© 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. 116293
    Prev
    Next
    INDEX
    Explanations

    documentary film titles

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

    document sections

    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
    B
    0.53
    L
    0.52
    ရာ
    0.44
    在
    0.44
    Շ
    0.43
     radar
    0.43
    得分
    0.43
     wheelchair
    0.43
    N
    0.43
    ใน
    0.42
    POSITIVE LOGITS
     производи
    0.53
     канцеля
    0.51
     лиш
    0.50
     이날
    0.50
    ances
    0.49
     кра
    0.49
     чи
    0.49
     міста
    0.48
     отре
    0.48
     мон
    0.48
    Activations Density 0.000%

    No Known Activations