© 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. 146417
    Prev
    Next
    INDEX
    Explanations

    producer in

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

    reports, documented

    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
    thereum
    0.56
    issued
    0.51
    verse
    0.48
    userId
    0.47
    reversible
    0.46
    f
    0.46
    paid
    0.45
    seg
    0.44
     placebo
    0.44
    BTC
    0.44
    POSITIVE LOGITS
     beschik
    0.55
     podía
    0.52
    鍱
    0.51
    宿舍
    0.49
    इकिल
    0.49
     knih
    0.49
     Règles
    0.49
     kiezen
    0.48
     schrij
    0.47
     arrêter
    0.47
    Activations Density 0.000%

    No Known Activations