© 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. 67560
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    aim for clarity or improvement

    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
    錠
    0.54
    Источник
    0.49
    🩺
    0.48
    ньої
    0.47
    種類
    0.46
    所
    0.46
    став
    0.45
    㽚
    0.45
    Télé
    0.45
    Traits
    0.45
    POSITIVE LOGITS
     White
    0.50
     triang
    0.47
     low
    0.47
     usa
    0.47
     SED
    0.46
     düşük
    0.46
     coward
    0.46
     porous
    0.45
     hago
    0.45
     Dough
    0.44
    Activations Density 0.001%

    No Known Activations