© 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. 75668
    Prev
    Next
    INDEX
    Explanations

    mounting posts

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

    specific models and measurements

    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
    ih
    0.52
    に関する法律
    0.46
     विष
    0.44
    Corners
    0.44
    ulitan
    0.43
    verg
    0.42
    ながら
    0.42
    ĺ
    0.42
     mucous
    0.41
     lieutenant
    0.41
    POSITIVE LOGITS
     Kimmel
    0.52
    elerini
    0.47
     Holmes
    0.46
     precedente
    0.45
     árabe
    0.45
    ഞ്ച്
    0.44
     Built
    0.44
    يط
    0.44
     Brendan
    0.43
     Vibrant
    0.43
    Activations Density 0.002%

    No Known Activations