© 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. 3211
    Prev
    Next
    INDEX
    Explanations

    generating scale

    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
    ↵↵
    0.44
     Bowls
    0.43
    Picture
    0.43
    全
    0.42
    4
    0.41
    マ
    0.40
    ゴ
    0.40
    core
    0.40
    0.40
    9
    0.40
    POSITIVE LOGITS
     problemi
    0.63
     рэгістра
    0.55
     permasalahan
    0.54
     OBSERV
    0.54
     sintomas
    0.54
     problemy
    0.52
     pengetahuan
    0.52
     mempelajari
    0.52
     masalah
    0.51
     جوہری
    0.51
    Activations Density 0.000%

    No Known Activations