© 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. 112201
    Prev
    Next
    INDEX
    Explanations

    cents per

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

    building a connection

    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
     histologic
    0.53
    <0x1E>
    0.50
     histology
    0.50
     மணியே
    0.47
    遠慮
    0.46
     पारित
    0.44
     histological
    0.44
     perempt
    0.44
     ხელისუფლების
    0.44
     அவனே
    0.43
    POSITIVE LOGITS
    犾
    0.47
    两个
    0.45
     Shaped
    0.44
    红
    0.44
    的所有
    0.43
    InputAction
    0.43
    拆
    0.43
    ρα
    0.42
    كو
    0.41
    اح
    0.41
    Activations Density 0.000%

    No Known Activations