© 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. 59382
    Prev
    Next
    INDEX
    Explanations

    foreign words and beer

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

    promises professional service

    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
    calup
    0.46
    ڼ
    0.46
     outta
    0.45
     drawers
    0.45
     refrigerators
    0.44
     timings
    0.44
     considerate
    0.43
     bullet
    0.43
     bikes
    0.42
    ність
    0.42
    POSITIVE LOGITS
    椪
    0.56
     впечатление
    0.53
    扃
    0.50
    范
    0.48
    员
    0.46
     пользова
    0.46
    平方
    0.44
    上演
    0.44
    Beer
    0.44
    澜
    0.44
    Activations Density 0.000%

    No Known Activations