© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12618
    Prev
    Next
    INDEX
    Explanations

    People

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ER
    0.53
    ру
    0.51
    ด
    0.50
    as
    0.49
     a
    0.47
    ↵
    0.47
    ку
    0.46
    ำ
    0.46
     airborne
    0.45
     humoral
    0.45
    POSITIVE LOGITS
    People
    0.71
     People
    0.60
    hood
    0.59
     mennesker
    0.55
     الناس
    0.54
     people
    0.52
    people
    0.52
    centric
    0.52
    মানুষ
    0.52
     ktorí
    0.51
    Activations Density 0.019%

    No Known Activations