© 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. 211292
    Prev
    Next
    INDEX
    Explanations

    battery offers records results

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

    Universal Healthcare

    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
     Verhältnis
    0.50
     जताया
    0.50
    練
    0.48
     ಎಂದ
    0.47
    分からない
    0.47
     voto
    0.46
    StarObject
    0.46
    検
    0.46
     தெரிவித்துள்ளது
    0.46
     เรือ
    0.46
    POSITIVE LOGITS
    i
    0.60
    is
    0.57
     c
    0.57
    ي
    0.54
    א
    0.52
     towards
    0.51
    حث
    0.50
    c
    0.49
     교육
    0.48
    މ
    0.47
    Activations Density 0.001%

    No Known Activations