© 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. 40-GEMMASCOPE-2-RES-262K
    7. 13634
    Prev
    Next
    INDEX
    Explanations

    ** highlight ** is ** power ** ** app ** ** trou ** ** individual ** ** code ** ** possible **

    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
     و
    0.47
    0.42
    ؛
    0.42
     که
    0.41
     أو
    0.39
     tipo
    0.39
     ها
    0.38
     suave
    0.37
    </h2>
    0.37
     projet
    0.37
    POSITIVE LOGITS
     других
    0.46
    <unused1861>
    0.43
     drugih
    0.41
    функциона
    0.40
    <unused278>
    0.40
    utiliser
    0.40
    अन्य
    0.40
    <unused696>
    0.40
     предотвра
    0.39
    <unused284>
    0.39
    Activations Density 0.114%

    No Known Activations