© 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. 21905
    Prev
    Next
    INDEX
    Explanations

    here again

    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
    বারি
    0.43
    ר
    0.40
    ﺮ
    0.40
    CALLBACK
    0.38
    יה
    0.38
     této
    0.38
     வகையில்
    0.37
    ش
    0.37
     voire
    0.37
     இங்கே
    0.36
    POSITIVE LOGITS
     instead
    0.54
    ifrån
    0.52
     when
    0.48
     statt
    0.46
     voor
    0.46
     anything
    0.45
    instead
    0.43
     fordi
    0.42
     amikor
    0.42
     cuando
    0.42
    Activations Density 0.043%

    No Known Activations