© 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. 102011
    Prev
    Next
    INDEX
    Explanations

    legal or factual basis

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

    renewal, obtained, roads

    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
     ench
    0.45
     millimeter
    0.44
    t
    0.44
    ;
    0.43
     reportedly
    0.41
    (,
    0.41
     Fahrenheit
    0.40
     immersing
    0.40
    >,
    0.40
     medley
    0.40
    POSITIVE LOGITS
    度和
    0.52
    และการ
    0.52
    人和
    0.50
     어려
    0.50
     සහ
    0.49
    志森
    0.48
    困难
    0.48
    तां
    0.47
    困難
    0.47
    佶
    0.46
    Activations Density 0.000%

    No Known Activations