© 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. 213343
    Prev
    Next
    INDEX
    Explanations

    salvation and sacred texts

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

    speaker malfunction

    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
    кара
    0.52
     시절
    0.49
    엿
    0.47
    暂
    0.46
    骑
    0.46
    Tags
    0.46
    注
    0.45
    Cara
    0.45
    胡
    0.45
    Перед
    0.44
    POSITIVE LOGITS
     impenetrable
    0.53
     intricately
    0.52
    ವಾಗಿರುತ್ತದೆ
    0.48
     centros
    0.48
     sacred
    0.47
     intricate
    0.47
     uncond
    0.47
     their
    0.47
     niiden
    0.47
     större
    0.46
    Activations Density 0.001%

    No Known Activations