© 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. 165179
    Prev
    Next
    INDEX
    Explanations

    excess, vinegar, reactions

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

    valid arguments or lists

    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
     模型
    0.51
     pursued
    0.47
     പരിശീല
    0.47
     നിൽ
    0.47
     பயிற்சி
    0.46
    ൻസ്
    0.46
     تجهیز
    0.46
    轳
    0.45
     succumbed
    0.45
     系统
    0.45
    POSITIVE LOGITS
    on
    0.61
    i
    0.46
    ne
    0.46
    0
    0.46
    as
    0.45
    Gran
    0.45
    合
    0.45
    LIST
    0.45
    did
    0.44
    聚
    0.43
    Activations Density 0.001%

    No Known Activations