© 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. 123789
    Prev
    Next
    INDEX
    Explanations

    blog, video, emails

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

    code structures

    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
     elas
    0.51
     Elise
    0.46
    三
    0.46
     underground
    0.44
     Angelica
    0.43
     sien
    0.42
     Elaine
    0.42
    （
    0.42
     Hild
    0.42
     Erika
    0.41
    POSITIVE LOGITS
    ormány
    0.46
     ഏത
    0.46
    ndash
    0.45
    Framebuffer
    0.45
     ដ
    0.45
    𒈾
    0.44
    腴
    0.44
     gastronom
    0.44
    hitting
    0.43
     sugli
    0.43
    Activations Density 0.000%

    No Known Activations