© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 80241
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ambat
    0.52
    third
    0.52
    ähn
    0.47
    iten
    0.45
    fourth
    0.45
    REDIR
    0.43
    earned
    0.43
    intersect
    0.43
    -\\
    0.42
    ar
    0.42
    POSITIVE LOGITS
     βιβ
    0.44
     Threats
    0.43
    ség
    0.41
     многие
    0.41
     việc
    0.40
    癌
    0.40
     suffit
    0.40
     Julie
    0.39
     faptul
    0.39
    ΝΑ
    0.39
    Activations Density 0.002%

    No Known Activations