© 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. 109450
    Prev
    Next
    INDEX
    Explanations

    categorize text

    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
    ه
    0.50
    热
    0.45
     এতদিন
    0.43
     Yarn
    0.43
    砻
    0.43
    ی
    0.42
    भी
    0.41
    나
    0.41
     Organization
    0.40
    })$,
    0.40
    POSITIVE LOGITS
     superficie
    0.59
     solide
    0.56
     Dateien
    0.55
     maximale
    0.51
     permukaan
    0.51
     erlaub
    0.50
    il
    0.49
     schermo
    0.48
     conforme
    0.48
     violates
    0.47
    Activations Density 0.004%

    No Known Activations