© 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. 97959
    Prev
    Next
    INDEX
    Explanations

    cooperating with, Squatter, convenient time

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

    lem me

    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
    volent
    0.49
    쎄
    0.48
     طلب
    0.47
    色の
    0.47
     poziom
    0.46
    ША
    0.46
     الطل
    0.45
     livelli
    0.45
     prépar
    0.44
    ദി
    0.44
    POSITIVE LOGITS
     ,[
    0.50
    ’
    0.48
    iposa
    0.47
    sms
    0.47
    sports
    0.46
    robot
    0.46
    ograf
    0.45
    item
    0.45
    '
    0.44
    symbols
    0.44
    Activations Density 0.001%

    No Known Activations