© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 17590
    Prev
    Next
    INDEX
    Explanations

    messing with

    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_16_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
    in
    1.16
    f
    1.05
    ak
    0.87
    for
    0.82
    st
    0.79
    ani
    0.79
    m
    0.79
    ly
    0.77
    9
    0.73
    </h2>
    0.73
    POSITIVE LOGITS
    는
    0.95
    は
    0.91
    ون
    0.88
    은
    0.85
    ۔
    0.80
     следующий
    0.77
     alterar
    0.75
     spécialement
    0.73
     proposé
    0.73
    是對
    0.72
    Activations Density 0.015%

    No Known Activations