© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 168201
    Prev
    Next
    INDEX
    Explanations

    time for events

    np_acts-logits-general · gemini-2.5-flash-lite

    categories, activations, and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ያንዳ
    0.49
    SpacerItem
    0.48
    梩
    0.47
    кса
    0.46
    SpawnEntry
    0.46
    ్రీన్
    0.45
    кість
    0.45
    ментів
    0.45
    менте
    0.45
    鴳
    0.44
    POSITIVE LOGITS
     vacancy
    0.54
     flames
    0.52
     subcutaneous
    0.52
     an
    0.50
     mouse
    0.49
     raken
    0.48
     benzene
    0.48
     hurricane
    0.48
     unemployment
    0.48
     gynec
    0.47
    Activations Density 0.000%

    No Known Activations