© 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. 40-GEMMASCOPE-2-RES-65K
    7. 48537
    Prev
    Next
    INDEX
    Explanations

    common words followed by specifics

    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_40_width_65k_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
     №
    0.44
     OSHA
    0.42
    क्रीम
    0.41
     Horizontal
    0.41
     Боли
    0.40
     $-
    0.39
     Expr
    0.39
     ОС
    0.39
     Dh
    0.39
     $\#
    0.38
    POSITIVE LOGITS
    braska
    0.38
    format
    0.38
    mittance
    0.38
    FO
    0.37
     gründ
    0.37
     ft
    0.37
    tz
    0.36
     ভাবে
    0.36
     victimization
    0.36
    imidazo
    0.36
    Activations Density 0.002%

    No Known Activations