© 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. 183732
    Prev
    Next
    INDEX
    Explanations

    web browsers

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

    web browser Safari

    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
     የበለጠ
    0.43
     Dateien
    0.41
    '
    0.40
    (!
    0.40
    ;
    0.40
     anxieties
    0.40
    قرار
    0.39
    (//
    0.39
    (/(
    0.39
    POSITIVE LOGITS
     দুই
    0.47
    蘞
    0.47
    लाम
    0.47
    ين
    0.46
     ทด
    0.45
    two
    0.45
    nourished
    0.44
    inink
    0.44
    綠
    0.44
     grueso
    0.43
    Activations Density 0.000%

    No Known Activations