© 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. 153251
    Prev
    Next
    INDEX
    Explanations

    organization mission

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

    magnetic, metal, senses

    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
     lub
    0.54
     conness
    0.52
     répart
    0.50
     octobre
    0.50
     Cognito
    0.49
     Swo
    0.48
    是很
    0.47
     legg
    0.46
    不由
    0.46
    ];
    0.45
    POSITIVE LOGITS
    adiq
    0.47
    Примечания
    0.47
    netic
    0.47
    grayscale
    0.47
    шите
    0.44
    дон
    0.44
     ネ
    0.44
    慎
    0.43
    नेटिक
    0.42
    Noir
    0.42
    Activations Density 0.001%

    No Known Activations