© 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. 85978
    Prev
    Next
    INDEX
    Explanations

    league regulations

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

    nectarines and stadiums

    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
     meromorphic
    0.45
     thisobject
    0.43
    bacteria
    0.42
    वियस
    0.42
    that
    0.41
    讨论
    0.41
    Ꮿ
    0.41
    texttt
    0.40
    ରି
    0.40
    عى
    0.40
    POSITIVE LOGITS
     sawing
    0.56
    사의
    0.50
     ハンド
    0.49
    Ę
    0.49
    iziModal
    0.48
     hiver
    0.46
    粹
    0.46
     envol
    0.46
    サウンド
    0.45
    ハンド
    0.45
    Activations Density 0.000%

    No Known Activations