© 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. 171941
    Prev
    Next
    INDEX
    Explanations

    own land, use IT, example, herself, tree ornament, fall

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

    seeking research inspirations

    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
     फैलाने
    0.43
     Juz
    0.42
    宥
    0.41
     طریقہ
    0.41
     ज़
    0.41
    }}-
    0.41
     ગુજરાત
    0.41
    imported
    0.41
    弩
    0.41
    ってしまう
    0.41
    POSITIVE LOGITS
    ↵↵
    0.54
    .
    0.49
     fortiter
    0.48
     seek
    0.48
     bid
    0.47
     immediately
    0.46
     calls
    0.46
     seeking
    0.46
     IT
    0.46
     endeavors
    0.46
    Activations Density 0.003%

    No Known Activations