© 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. 110506
    Prev
    Next
    INDEX
    Explanations

    numbers followed by stats

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

    stories and finance

    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
    をお
    0.59
     verwenden
    0.51
    ধ
    0.51
    Embedding
    0.50
    Embed
    0.49
    experiment
    0.47
     экспери
    0.47
    凄
    0.47
     embed
    0.47
     experiment
    0.47
    POSITIVE LOGITS
    y
    0.47
    ృష్టి
    0.42
     Sainsbury
    0.41
    ilane
    0.41
    gare
    0.40
     Succession
    0.40
    طان
    0.40
    валися
    0.40
    ตรฐาน
    0.40
     Country
    0.39
    Activations Density 0.000%

    No Known Activations