© 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. 99454
    Prev
    Next
    INDEX
    Explanations

    final plans or not hesitate

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

    places and bags

    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
     Ach
    0.48
     '//
    0.47
     歩
    0.46
     PropTypes
    0.46
     香港
    0.46
     Engaging
    0.46
    BackendAuth
    0.44
     ({\
    0.43
     Hell
    0.43
     組
    0.43
    POSITIVE LOGITS
    सी
    0.59
     भग्न
    0.52
     സൂര്യ
    0.50
    ırmızı
    0.48
     musi
    0.47
     पातळी
    0.47
    วัต
    0.47
    국
    0.46
     ഭാര്യ
    0.46
    闂
    0.46
    Activations Density 0.000%

    No Known Activations