© 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. 78634
    Prev
    Next
    INDEX
    Explanations

    list separators and content

    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
    닝
    0.43
    redients
    0.41
     complicate
    0.40
     instantiated
    0.40
    은
    0.40
     etx
    0.39
     consumed
    0.39
    lessly
    0.38
     subsum
    0.38
     ternary
    0.38
    POSITIVE LOGITS
    </em>
    0.45
     Rib
    0.41
    スカ
    0.40
    髅
    0.40
     Еўро
    0.39
     Букмекердик
    0.38
     Generations
    0.38
    Edwards
    0.38
     गौरतलब
    0.37
    Rib
    0.36
    Activations Density 0.003%

    No Known Activations