© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 231452
    Prev
    Next
    INDEX
    Explanations

    might fail or will work

    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
    Ợ
    0.50
    儉
    0.45
    º
    0.45
    ECD
    0.45
    CAM
    0.44
     observar
    0.44
    鄧
    0.44
    ించాడు
    0.44
    Ы
    0.44
    ్వ
    0.43
    POSITIVE LOGITS
     future
    0.54
     전
    0.53
     confusion
    0.49
     debut
    0.48
    ล
    0.48
     nose
    0.48
     해야
    0.48
     fair
    0.47
     ที
    0.47
    แต
    0.46
    Activations Density 0.000%

    No Known Activations