© 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. 217997
    Prev
    Next
    INDEX
    Explanations

    exercise, fit, usage, combine

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

    common nouns and punctuation

    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
    Negative Logits
    INST
    0.45
    」
    0.45
    仲
    0.44
    (){}
    0.44
    Always
    0.43
     trapped
    0.41
     nunca
    0.41
    كينا
    0.41
    ILS
    0.41
    滋
    0.41
    POSITIVE LOGITS
    മാനം
    0.48
     ettiği
    0.45
     montant
    0.44
     CHP
    0.43
     ενός
    0.42
    范围内
    0.42
     लिहाज
    0.42
    শেষে
    0.41
     versatile
    0.41
    সমস্ত
    0.41
    Activations Density 0.003%

    No Known Activations