© 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. 6688
    Prev
    Next
    INDEX
    Explanations

    international entities or discussions

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

    questions and definitions

    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
    J
    0.52
    EL
    0.52
    LER
    0.49
    PORT
    0.46
    AN
    0.46
     সন্ধ্যার
    0.46
    HI
    0.46
    Memorial
    0.46
    AJ
    0.45
    P
    0.45
    POSITIVE LOGITS
     sapon
    0.53
     Citibank
    0.51
     DID
    0.50
    ibrate
    0.50
     रे
    0.49
     Gazprom
    0.49
     rán
    0.48
     मार
    0.48
     prodig
    0.48
     puppets
    0.48
    Activations Density 0.000%

    No Known Activations