© 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. 223109
    Prev
    Next
    INDEX
    Explanations

    must be, courses in, very well, namely, contents of

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

    summary points sections introduction

    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
    ↵
    0.53
    <0xE3>
    0.51
      
    0.47
    <strong>
    0.46
    <0xC2>
    0.44
    ณะ
    0.43
     They
    0.42
     Acho
    0.41
    {"
    0.41
     كلهم
    0.41
    POSITIVE LOGITS
    ിയ്
    0.52
    墂
    0.50
    中所
    0.48
    涳
    0.48
    文档
    0.48
    యన్స్
    0.47
    咊
    0.46
     فريبيس
    0.46
    راہ
    0.46
    洳
    0.46
    Activations Density 0.000%

    No Known Activations