© 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. 38683
    Prev
    Next
    INDEX
    Explanations

    specific places and concepts

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

    analyzing text and code

    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
    ATE
    0.48
    rm
    0.46
    INTER
    0.45
    CH
    0.44
    ad
    0.43
    정
    0.43
    just
    0.43
    I
    0.43
    IN
    0.43
    IB
    0.42
    POSITIVE LOGITS
     रिए
    0.48
     пон
    0.45
    ۣ
    0.45
    לת
    0.44
     duração
    0.44
     richtig
    0.43
     dreaded
    0.42
    的地
    0.42
     menonton
    0.42
     piercings
    0.42
    Activations Density 0.000%

    No Known Activations