© 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. 195318
    Prev
    Next
    INDEX
    Explanations

    leadership andtransmitter toexperts !buyers evermodes, dady

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

    standard kitchen, CPU, bands, models

    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
    判定
    0.52
     Valuation
    0.46
     timezone
    0.43
    っと
    0.43
     discriminator
    0.42
    FI
    0.42
     kiosk
    0.42
    。
    0.42
    izzano
    0.42
     signal
    0.41
    POSITIVE LOGITS
    agricult
    0.49
     arquitect
    0.47
     pobreza
    0.47
     nông
    0.46
    裒
    0.45
     Erwach
    0.45
     COOK
    0.45
     nấu
    0.45
     cookbooks
    0.44
     À
    0.44
    Activations Density 0.001%

    No Known Activations