© 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-262K
    7. 213956
    Prev
    Next
    INDEX
    Explanations

    quotes attributed to figures

    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_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
     заку
    0.43
    Promo
    0.40
     फायर
    0.38
    Suk
    0.38
    MovieDetails
    0.37
    觛
    0.37
    ੧
    0.37
    蝿
    0.37
    TakeVideo
    0.37
    受注
    0.37
    POSITIVE LOGITS
     attributed
    2.61
     ascribed
    2.25
     attribu
    2.20
     attribution
    2.19
    attributed
    2.16
     atribu
    2.13
     atrib
    2.06
     attrib
    1.98
     attributing
    1.91
    attribution
    1.88
    Activations Density 0.058%

    No Known Activations