© 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. 130782
    Prev
    Next
    INDEX
    Explanations

    acute disorder

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

    generally, typically, about

    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
    actives
    0.52
    юн
    0.49
    そうだ
    0.49
    ワ
    0.47
     iskust
    0.46
    ヴェル
    0.46
    得意
    0.46
    ブ
    0.46
    ﾈ
    0.45
     nanofibers
    0.45
    POSITIVE LOGITS
     Changed
    0.47
     Packing
    0.47
     Due
    0.46
     Boolean
    0.46
    अलग
    0.46
     Because
    0.43
     đều
    0.43
     Com
    0.42
     Change
    0.42
     ،
    0.42
    Activations Density 0.000%

    No Known Activations