© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 13528
    Prev
    Next
    INDEX
    Explanations

    gold medals

    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
    σης
    0.68
    a
    0.68
     که
    0.67
    णी
    0.65
    랗
    0.61
    acu
    0.61
    bills
    0.60
     disorderly
    0.59
    ungnya
    0.59
     gonad
    0.59
    POSITIVE LOGITS
    </h2>
    0.74
     Defin
    0.68
     I
    0.66
     L
    0.64
     E
    0.64
    ↵
    0.62
    </h1>
    0.62
    ></
    0.62
    วัน
    0.62
     Ferien
    0.61
    Activations Density 0.001%

    No Known Activations