© 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. 76284
    Prev
    Next
    INDEX
    Explanations

    conversation and interviews

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

    describing actions and states

    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
    రించ
    0.50
    병원
    0.49
     オレンジ
    0.48
     arouse
    0.47
     harmonique
    0.46
    鎊
    0.46
     abandon
    0.46
     Weihn
    0.46
    苳
    0.46
     awaken
    0.46
    POSITIVE LOGITS
    in
    0.54
    value
    0.50
    question
    0.50
    treasure
    0.50
    thought
    0.50
    designed
    0.50
    conversation
    0.50
    liberal
    0.50
    likely
    0.49
    questions
    0.48
    Activations Density 0.000%

    No Known Activations