© 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. 30519
    Prev
    Next
    INDEX
    Explanations

    Parkland school and Prince Mohammed

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

    tracking progress

    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
     día
    0.46
     empires
    0.46
     salido
    0.46
     yd
    0.46
     Dedu
    0.45
     facere
    0.45
     日
    0.44
    oplast
    0.44
     đáy
    0.44
    дир
    0.44
    POSITIVE LOGITS
    atum
    0.45
    华人
    0.44
    情节
    0.43
    اتب
    0.43
    奮
    0.43
    OR
    0.43
     trache
    0.42
    Bris
    0.42
    私募基金
    0.42
     upregulation
    0.42
    Activations Density 0.001%

    No Known Activations