© 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. 73295
    Prev
    Next
    INDEX
    Explanations

    out of

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

    clarifying intended meaning in corrections

    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
     applicability
    0.46
    謂
    0.46
     pathogenicity
    0.45
     maximizing
    0.45
    제로
    0.45
    莫
    0.45
    肺
    0.44
     pathogenic
    0.43
    मो
    0.43
    acceleration
    0.42
    POSITIVE LOGITS
     Lumber
    0.54
     Consumer
    0.46
     Lyn
    0.45
     comprend
    0.45
    üman
    0.44
     Customers
    0.44
     ନ
    0.44
    Timber
    0.44
     নিবাস
    0.44
    Consumer
    0.43
    Activations Density 0.000%

    No Known Activations