© 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. 148364
    Prev
    Next
    INDEX
    Explanations

    local labor, tapping of, has entered

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

    what you can do

    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
     tó
    0.46
    émi
    0.45
    토
    0.44
    咫
    0.44
    يز
    0.43
    цької
    0.43
    馈
    0.43
    يس
    0.43
    ست
    0.42
    那
    0.42
    POSITIVE LOGITS
     investir
    0.46
     escond
    0.46
    cutaneous
    0.44
     gangsters
    0.44
    `${
    0.43
     delinqu
    0.42
    ወ
    0.42
     गैंग
    0.42
     practition
    0.42
     displaystyle
    0.42
    Activations Density 0.000%

    No Known Activations