© 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. 17631
    Prev
    Next
    INDEX
    Explanations

    accessible on, they are, our

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

    step plan4 operations

    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
    构建
    0.41
    igd
    0.41
    和一个
    0.41
     여러분
    0.40
     연습
    0.40
     اسئله
    0.40
    龇
    0.39
     ạ
    0.39
     배워
    0.39
     изу
    0.38
    POSITIVE LOGITS
    ce
    0.45
     cenderung
    0.43
    rites
    0.43
     celui
    0.40
    立ち
    0.40
     माध्यमा
    0.40
     clergy
    0.40
    m
    0.40
    meno
    0.39
    ble
    0.38
    Activations Density 0.000%

    No Known Activations