© 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. 62064
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis or period then word

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

    SQL code snippets

    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
    л
    0.65
    ل
    0.52
    r
    0.47
    ש
    0.46
    ر
    0.45
    することで
    0.44
     attendant
    0.44
    bertson
    0.43
     parce
    0.43
    จน
    0.43
    POSITIVE LOGITS
     Rxh
    0.45
    ipp
    0.44
     உணர
    0.44
    浈
    0.42
     বোঝার
    0.41
     ووٹ
    0.41
     Earlier
    0.40
     رائے
    0.40
     آموزش
    0.40
     그는
    0.40
    Activations Density 0.001%

    No Known Activations