© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 129828
    Prev
    Next
    INDEX
    Explanations

    found to get into

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

    ratio, approx, around

    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
    Negative Logits
     해주
    0.50
     domać
    0.50
     đỉnh
    0.48
     ناخذ
    0.46
     pengg
    0.46
    getCQL
    0.45
    øk
    0.43
    椋
    0.43
     দেখবেন
    0.42
     nějak
    0.42
    POSITIVE LOGITS
     өчен
    0.44
    óta
    0.42
     fearful
    0.42
     यूनिवर्सल
    0.42
    ഡ്
    0.42
    انون
    0.42
     Gentlemen
    0.42
    uzten
    0.42
    anned
    0.41
    Hallo
    0.41
    Activations Density 0.001%

    No Known Activations