© 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. 88624
    Prev
    Next
    INDEX
    Explanations

    fashion area, long cut, PR stakes

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

    preventing or hindering actions

    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
    也都
    0.47
    histor
    0.45
     પહે
    0.45
    あるいは
    0.44
    moniker
    0.42
    cognitive
    0.42
    聞
    0.42
    consistent
    0.40
     ឬ
    0.40
     الجديدة
    0.40
    POSITIVE LOGITS
     banjir
    0.48
     setValue
    0.45
    ："
    0.45
     :"
    0.45
    }">
    0.44
    เพราะ
    0.44
     causality
    0.44
    เพียง
    0.43
     prevents
    0.43
    控件
    0.42
    Activations Density 0.001%

    No Known Activations