© 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. 13967
    Prev
    Next
    INDEX
    Explanations

    common word followed by specific noun

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

    blinking, forming, protecting, promise, accepting

    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
    ↵↵
    0.54
     coding
    0.54
    编码
    0.46
    در
    0.44
    шему
    0.44
    是什么
    0.43
    状况
    0.43
    码
    0.42
    Ger
    0.42
     codes
    0.42
    POSITIVE LOGITS
    selfobj
    0.53
    ಟ್
    0.47
     peau
    0.46
     لئے
    0.46
     奥
    0.46
    farm
    0.45
     vinos
    0.45
     lilies
    0.45
     çant
    0.45
    ण्यात
    0.45
    Activations Density 0.000%

    No Known Activations