© 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. 31-GEMMASCOPE-2-RES-262K
    7. 100124
    Prev
    Next
    INDEX
    Explanations

    Subject-Predicate-Object triplets

    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_31_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
     headcount
    0.47
    и
    0.46
    swick
    0.43
    وبي
    0.42
     flowchart
    0.41
     carri
    0.41
    ikopter
    0.41
     swelling
    0.41
     بيان
    0.40
    EntityFramework
    0.40
    POSITIVE LOGITS
    لوں
    0.46
     equivale
    0.45
    टरीना
    0.44
    components
    0.43
    ０
    0.43
     تاکہ
    0.43
    denoted
    0.43
     roupas
    0.42
     Wade
    0.42
    قیق
    0.41
    Activations Density 0.003%

    No Known Activations