© 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. 245057
    Prev
    Next
    INDEX
    Explanations

    led replacements, classification process

    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
     Lehenga
    0.53
     时尚
    0.53
    шивания
    0.52
     컬러
    0.52
    杝
    0.51
     왼
    0.50
    鸣
    0.50
    妸
    0.50
     ivvu
    0.48
    黟
    0.48
    POSITIVE LOGITS
     clerk
    0.50
     say
    0.49
     reporting
    0.48
     broker
    0.48
    in
    0.47
     location
    0.46
     phone
    0.46
     maker
    0.44
     spokesperson
    0.44
     committee
    0.44
    Activations Density 0.000%

    No Known Activations