© 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. 163429
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    my own development

    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
    ﻧ
    0.49
    KE
    0.47
    0.44
    い
    0.43
    NJ
    0.43
     lasci
    0.43
    عهد
    0.43
    皙
    0.43
     ("[
    0.42
     remedi
    0.42
    POSITIVE LOGITS
     ہوجائیں
    0.48
     бактери
    0.46
     መጠን
    0.45
     потреб
    0.44
     पॉइंट
    0.42
     মিনি
    0.42
     باتیں
    0.42
     потеря
    0.42
     වෙ
    0.42
     вещества
    0.42
    Activations Density 0.000%

    No Known Activations