© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 10013
    Prev
    Next
    INDEX
    Explanations

    presentation, poly, provide

    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
    WIT
    0.51
     fisc
    0.49
    禰
    0.47
    \%
    0.46
    linecap
    0.46
    iae
    0.46
    鼗
    0.46
    ための
    0.45
    𒃻
    0.45
    سے
    0.44
    POSITIVE LOGITS
     dehyd
    0.50
     bodysuit
    0.50
     BES
    0.49
     event
    0.48
     tornado
    0.47
     OBJ
    0.47
     DEL
    0.46
     best
    0.46
     Best
    0.46
     EVENT
    0.46
    Activations Density 0.004%

    No Known Activations