© 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. 74947
    Prev
    Next
    INDEX
    Explanations

    determiner or adjective before noun

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

    State Level

    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
    物品
    0.57
    契約
    0.51
    业务
    0.49
    <0xF0>
    0.48
    場合は
    0.48
    詐
    0.48
    買
    0.47
    第三方
    0.47
    右
    0.47
    個人
    0.47
    POSITIVE LOGITS
    òn
    0.48
    matical
    0.43
    jeh
    0.42
     Paine
    0.41
     Submission
    0.40
    ȏ
    0.39
    esen
    0.39
     Deo
    0.39
    âne
    0.39
     LGB
    0.39
    Activations Density 0.001%

    No Known Activations