© 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. 52537
    Prev
    Next
    INDEX
    Explanations

    bird bath

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

    computer vision, intellectual property

    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
    ारे
    0.54
    सारी
    0.49
    많은
    0.47
    Э
    0.46
    מש
    0.45
    ഏ
    0.45
    serious
    0.44
    Боль
    0.44
     poważ
    0.43
    Օ
    0.42
    POSITIVE LOGITS
     मृतक
    0.51
     appellee
    0.45
     masked
    0.42
     फ़
    0.42
    rizzle
    0.40
     glob
    0.40
    ração
    0.40
    uelva
    0.40
     Japan
    0.39
    ulosa
    0.39
    Activations Density 0.000%

    No Known Activations