© 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. 78460
    Prev
    Next
    INDEX
    Explanations

    intends on

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

    materials for

    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
    ៤
    0.50
    upan
    0.49
     株式会社
    0.49
     Chase
    0.47
     youthful
    0.46
    wagen
    0.46
     Corbyn
    0.46
     aromas
    0.46
    コピー
    0.46
     "")
    0.46
    POSITIVE LOGITS
     экономических
    0.47
    خن
    0.44
     било
    0.43
    였
    0.42
    FrameLayout
    0.42
    廣
    0.42
     giải
    0.42
     temu
    0.41
    りました
    0.41
    າກ
    0.41
    Activations Density 0.000%

    No Known Activations