© 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. 184719
    Prev
    Next
    INDEX
    Explanations

    pay to drop salary

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

    sissy girl identity

    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
    詳細
    0.50
    详细
    0.48
     lakhs
    0.46
    锴
    0.45
    িলাম
    0.45
    이었다
    0.45
    萜
    0.44
    لما
    0.43
    ﾏ
    0.43
     اصلی
    0.43
    POSITIVE LOGITS
     brû
    0.48
     Numero
    0.46
     vej
    0.45
     gyd
    0.42
     năng
    0.42
    变革
    0.42
     cultura
    0.42
    ansk
    0.42
    [["
    0.42
     să
    0.41
    Activations Density 0.000%

    No Known Activations