© 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. 166040
    Prev
    Next
    INDEX
    Explanations

    Cytoplasm, wash, sorrow, 因工作

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

    vision, washing, integer, segment

    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
    サンプル
    0.53
    スカ
    0.48
    gr
    0.48
    goo
    0.47
    0
    0.46
     താര
    0.43
     கிலோ
    0.42
    RELATIVE
    0.42
    ▛
    0.42
    REETYPE
    0.41
    POSITIVE LOGITS
    िलाई
    0.49
    inputSet
    0.46
     llevado
    0.46
    esity
    0.45
    有所
    0.43
    ختلف
    0.43
     गहरी
    0.43
    ждены
    0.42
     সন্
    0.42
    lisher
    0.42
    Activations Density 0.000%

    No Known Activations