© 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. 57441
    Prev
    Next
    INDEX
    Explanations

    roulette experience, high level

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

    non-English characters

    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
     CRIM
    0.55
     CRIMINAL
    0.53
     RANK
    0.53
     AVE
    0.52
    y
    0.52
    ullie
    0.50
     vatth
    0.50
    ❜
    0.50
     FRIEND
    0.50
     سای
    0.49
    POSITIVE LOGITS
    లి
    0.50
    лы
    0.46
    驰
    0.46
    stackoverflow
    0.45
    外界
    0.45
    łoś
    0.45
    лся
    0.44
    法语
    0.44
    过后
    0.44
    规划
    0.43
    Activations Density 0.000%

    No Known Activations