© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 85886
    Prev
    Next
    INDEX
    Explanations

    names and application information

    np_acts-logits-general · gemini-2.5-flash-lite

    safety, disclaimers, technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deletions
    0.49
    ெல்ல
    0.46
     Shet
    0.46
     Kategorie
    0.45
     declines
    0.44
     disagrees
    0.44
     Dispose
    0.44
    ޅ
    0.44
     shelters
    0.44
     defeat
    0.43
    POSITIVE LOGITS
    asing
    0.45
    JF
    0.45
    漾
    0.44
    eraient
    0.43
    getPackage
    0.43
    AppLink
    0.43
     തുട
    0.43
     প্রধানমন্ত্রীর
    0.43
    arten
    0.42
    Ajax
    0.42
    Activations Density 0.000%

    No Known Activations