© 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. 130614
    Prev
    Next
    INDEX
    Explanations

    wedding ring

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

    supports day-to-day operations

    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
    DEV
    0.51
     verbally
    0.49
     riserv
    0.48
    ADD
    0.47
    ISA
    0.46
     distribute
    0.46
    ೨
    0.46
    CREATE
    0.45
    QUI
    0.44
    AGE
    0.43
    POSITIVE LOGITS
     Iz
    0.54
     Sarajevo
    0.52
     😍
    0.50
    😍
    0.50
    atosis
    0.48
    ی
    0.48
     Andaman
    0.48
    이터
    0.47
     iz
    0.47
    atot
    0.46
    Activations Density 0.000%

    No Known Activations