© 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. 11510
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

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

    pointers upwardsevaporate quicklypurchased within

    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
    ufu
    0.41
     persisted
    0.37
    ems
    0.36
    usic
    0.36
     Hagan
    0.36
    }});
    0.35
     Sellers
    0.34
     ÷
    0.34
     Vn
    0.34
    ati
    0.34
    POSITIVE LOGITS
    機構
    0.46
    мену
    0.43
     mécanisme
    0.41
    hiver
    0.39
    𝒹
    0.39
    étique
    0.39
    ера
    0.39
    درا
    0.39
    邬
    0.39
    冠軍
    0.38
    Activations Density 0.000%

    No Known Activations