© 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. 241237
    Prev
    Next
    INDEX
    Explanations

    Frank Underwood

    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
     рит
    0.49
     территория
    0.48
     скла
    0.48
     зи
    0.45
     Breeders
    0.45
     ربعه
    0.44
    )}"
    0.43
     कॉनकॉर्ड
    0.43
     тест
    0.43
     vecin
    0.42
    POSITIVE LOGITS
    اری
    0.53
    amento
    0.52
    ۹
    0.50
     flavours
    0.49
     Shand
    0.47
    ?
    0.47
    وی
    0.46
    세요
    0.46
     Mudah
    0.46
    '
    0.46
    Activations Density 0.001%

    No Known Activations