© 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. 21806
    Prev
    Next
    INDEX
    Explanations

    I will

    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
    শিদ
    0.43
    inspiration
    0.41
     Inspiration
    0.40
     පළ
    0.40
    form
    0.39
     Danny
    0.38
     Pharmacology
    0.37
    ísmo
    0.37
     traslado
    0.36
     --------");
    0.36
    POSITIVE LOGITS
    Texas
    0.45
    AV
    0.43
    CCSD
    0.43
     km
    0.43
     কর্মকর্তা
    0.41
    Fc
    0.41
    Gr
    0.41
    视频
    0.41
    立
    0.41
     اللي
    0.40
    Activations Density 0.001%

    No Known Activations