© 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. 33302
    Prev
    Next
    INDEX
    Explanations

    razorreceived laundryoccupantsJahre Ess

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

    data storage and IoT market

    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
    成果
    0.52
    信任
    0.48
    連接
    0.47
    ೯
    0.46
     букме
    0.46
    xcsche
    0.45
    快
    0.44
    pathTemplates
    0.44
    字
    0.44
    旋
    0.44
    POSITIVE LOGITS
     Comics
    0.54
     Sh
    0.53
    </h3>
    0.53
     The
    0.52
     Männer
    0.52
     tätig
    0.52
     What
    0.50
     Chrys
    0.50
     Is
    0.50
     Mrs
    0.50
    Activations Density 0.000%

    No Known Activations