© 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. 187091
    Prev
    Next
    INDEX
    Explanations

    insured, sun, main, average

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

    create functions, prices need

    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
     experiencing
    0.52
    ش
    0.50
    泰国
    0.46
    未来
    0.44
    بتدي
    0.44
    سا
    0.43
     residing
    0.43
    过后
    0.43
    輿
    0.42
    રમાં
    0.41
    POSITIVE LOGITS
     undertook
    0.49
     ആയിരുന്നു
    0.49
     كان
    0.48
    arus
    0.48
    umbrella
    0.47
    मैन
    0.47
    arma
    0.46
     Flies
    0.45
     היה
    0.45
    heben
    0.45
    Activations Density 0.000%

    No Known Activations