© 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. 53602
    Prev
    Next
    INDEX
    Explanations

    a leading official description

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

    average

    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
     BadRequest
    0.49
    ದ
    0.49
    🎞
    0.49
    會在
    0.46
    ⏱
    0.46
    🗓
    0.45
    ៣
    0.44
    נת
    0.43
     Sơn
    0.43
    ையின்
    0.42
    POSITIVE LOGITS
     Fayette
    0.52
     vapors
    0.49
     refin
    0.48
     raf
    0.48
     gouttes
    0.45
     ramo
    0.45
     продажи
    0.44
     honor
    0.43
     avg
    0.42
     savons
    0.42
    Activations Density 0.000%

    No Known Activations