© 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. 83238
    Prev
    Next
    INDEX
    Explanations

    English, Multilingual Contexts

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

    assisted in projects

    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
     ۲
    0.61
     २
    0.60
    ２
    0.59
    ］
    0.58
    ｝
    0.57
    ＾＾
    0.57
    กลาง
    0.57
     ४
    0.54
     ۵
    0.54
    ಾಗಲೇ
    0.54
    POSITIVE LOGITS
     in
    0.76
    在
    0.57
     děti
    0.53
     dedicate
    0.52
    绝对
    0.52
    看过
    0.50
     niemals
    0.50
     incluidas
    0.49
     في
    0.49
     inorder
    0.48
    Activations Density 0.005%

    No Known Activations