© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 139935
    Prev
    Next
    INDEX
    Explanations

    latex itemize environments

    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_16_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
     in
    1.04
     are
    0.98
     of
    0.95
     on
    0.87
    は
    0.79
     it
    0.73
     incentives
    0.73
    ERN
    0.73
     impenetrable
    0.71
     at
    0.70
    POSITIVE LOGITS
    0.93
    ad
    0.88
    at
    0.79
    ap
    0.79
    ك
    0.79
    us
    0.76
    f
    0.76
    fruit
    0.74
    els
    0.70
    og
    0.67
    Activations Density 0.001%

    No Known Activations