© 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. 243270
    Prev
    Next
    INDEX
    Explanations

    site preparation and design

    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
    प्पी
    0.54
    स्टैंड
    0.49
    ynes
    0.46
     îng
    0.46
    реги
    0.45
     fungicides
    0.45
    ỵ
    0.44
    reflectionCamera
    0.44
    า
    0.44
    롬
    0.43
    POSITIVE LOGITS
     %\
    0.38
     analytics
    0.38
     pärast
    0.38
     organs
    0.38
    AQ
    0.37
     lern
    0.37
     tart
    0.37
     στην
    0.37
    нів
    0.37
     sce
    0.37
    Activations Density 0.000%

    No Known Activations