© 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. 249843
    Prev
    Next
    INDEX
    Explanations

    technical analysis or support

    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
    🅷
    0.44
     fclose
    0.43
    に示す
    0.42
    inputenc
    0.42
     प्रकाशित
    0.40
    Ụ
    0.40
    sembling
    0.40
     सबसे
    0.39
    📜
    0.39
     int
    0.39
    POSITIVE LOGITS
    acre
    0.47
     waren
    0.46
     rocked
    0.45
    EPA
    0.45
     kamen
    0.45
    étaient
    0.45
    +.
    0.44
     Bewertung
    0.44
    quark
    0.43
    africa
    0.43
    Activations Density 0.000%

    No Known Activations