© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 202984
    Prev
    Next
    INDEX
    Explanations

    organizational terms and concepts

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

    property, conditional, creator, god, hash

    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
    </
    0.45
     heighten
    0.42
     .
    0.42
    條件
    0.42
    =>
    0.41
     Chees
    0.41
    스는
    0.40
    sü
    0.40
    સ
    0.39
    슴
    0.39
    POSITIVE LOGITS
    นั่ง
    0.57
    inventory
    0.54
     ரூ
    0.50
     الان
    0.50
     રૂપિયા
    0.50
     ರಾ
    0.49
     склада
    0.49
    取り付け
    0.49
    Inventory
    0.48
     ഉപകരണ
    0.48
    Activations Density 0.000%

    No Known Activations