© 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. 112260
    Prev
    Next
    INDEX
    Explanations

    whaimin .com

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

    python code

    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
    フォー
    0.52
    わたし
    0.48
    䤚
    0.48
    Revised
    0.46
    ــــ
    0.45
     Consequently
    0.45
    ⤠
    0.44
    🕕
    0.43
    裵
    0.43
    ਫ਼
    0.43
    POSITIVE LOGITS
    (()=>{
    0.55
    v
    0.51
     FullHD
    0.50
     prenez
    0.47
    ={()=>
    0.46
     येथ
    0.46
     paru
    0.46
    dv
    0.46
    expire
    0.46
     ltd
    0.45
    Activations Density 0.007%

    No Known Activations