© 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. 89435
    Prev
    Next
    INDEX
    Explanations

    business names and types

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

    origins and breakdown

    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
    ଢ
    0.57
    ಾಣ
    0.48
    ତା
    0.46
    🖍
    0.46
    𝘀
    0.46
    𝗸
    0.46
    যা
    0.45
    ଞ
    0.45
    bigvee
    0.44
     obtenidos
    0.44
    POSITIVE LOGITS
     We
    0.50
    Group
    0.50
     Buddhists
    0.47
     University
    0.47
     Group
    0.46
     College
    0.46
     Michaelmas
    0.45
     Gruppe
    0.44
     Accepted
    0.44
     Holy
    0.43
    Activations Density 0.001%

    No Known Activations