© 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. 238324
    Prev
    Next
    INDEX
    Explanations

    run down

    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
    兩個
    0.50
     Mitochondrial
    0.47
    २
    0.47
    这两个
    0.46
    两个
    0.45
    кування
    0.45
    വർ
    0.45
     zwei
    0.45
     zweiten
    0.44
    აქ
    0.44
    POSITIVE LOGITS
     ye
    0.46
     paste
    0.42
    ata
    0.42
    ate
    0.40
    顎
    0.40
    yatiti
    0.39
    aty
    0.38
     تی
    0.38
    ">$
    0.38
    ture
    0.38
    Activations Density 0.000%

    No Known Activations