© 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. 31-GEMMASCOPE-2-RES-262K
    7. 44013
    Prev
    Next
    INDEX
    Explanations

    about radar Quick

    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
     gamme
    0.59
     deactivated
    0.59
     spool
    0.57
     =
    0.54
     tower
    0.54
     toz
    0.53
     tongs
    0.53
     chuva
    0.53
     brooch
    0.52
     studio
    0.52
    POSITIVE LOGITS
    í
    0.54
    му
    0.51
    sí
    0.51
    رد
    0.49
    ô
    0.47
    à
    0.47
    sche
    0.46
    certain
    0.46
    zü
    0.45
    μ
    0.45
    Activations Density 0.001%

    No Known Activations