© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79181
    Prev
    Next
    INDEX
    Explanations

    beginning and monitoring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    秏
    0.47
     PLL
    0.46
     ذریعے
    0.46
     చెందిన
    0.45
    س
    0.44
    ycznych
    0.44
    𝙨
    0.43
     Đình
    0.43
     русский
    0.43
     traumatic
    0.43
    POSITIVE LOGITS
     interpr
    0.52
     kilomètres
    0.48
     rivol
    0.44
    一颗
    0.43
     sought
    0.42
    oming
    0.42
     dalle
    0.42
     टारगेट
    0.42
    探
    0.41
     revient
    0.41
    Activations Density 0.003%

    No Known Activations