© 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. 237161
    Prev
    Next
    INDEX
    Explanations

    law and damage

    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
     முடிந்த
    0.54
    nije
    0.52
     زاويه
    0.51
     должность
    0.49
     પોતા
    0.47
     తర
    0.47
    ﮅ
    0.46
     પોતાની
    0.46
    ayout
    0.46
    缓解
    0.45
    POSITIVE LOGITS
     boas
    0.57
    s
    0.49
     notifies
    0.49
    II
    0.47
    es
    0.47
     bea
    0.46
    a
    0.46
     boa
    0.45
     exista
    0.44
    لین
    0.44
    Activations Density 0.001%

    No Known Activations