© 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. 205563
    Prev
    Next
    INDEX
    Explanations

    explaining things

    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
    Not in Any Lists

    No Comments

    Negative Logits
     devra
    0.47
     intégré
    0.44
     dovr
    0.43
     dovrà
    0.42
     musicales
    0.41
    你
    0.41
     allongé
    0.40
     godziny
    0.40
     encoding
    0.40
     encode
    0.40
    POSITIVE LOGITS
    -------
    0.49
     שה
    0.46
    一篇
    0.45
     रचा
    0.43
    ------
    0.43
    ли
    0.42
     nonfiction
    0.42
     বিস্তারিত
    0.42
    оні
    0.42
    -----
    0.41
    Activations Density 0.005%

    No Known Activations