© 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. 128598
    Prev
    Next
    INDEX
    Explanations

    adventure/RPG

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

    AI, NLP, tools, effort, fixes

    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
    kách
    0.54
    โต
    0.50
     Chatur
    0.46
     konzent
    0.46
    ruth
    0.46
    慵
    0.46
    綎
    0.46
     جم
    0.45
    तून
    0.45
    国道
    0.45
    POSITIVE LOGITS
    0.48
     laboratory
    0.46
     embodiments
    0.45
     agents
    0.44
     -
    0.41
     analogues
    0.41
     analogs
    0.41
     quantum
    0.41
     prevailed
    0.41
     dialects
    0.41
    Activations Density 0.002%

    No Known Activations