© 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. 38976
    Prev
    Next
    INDEX
    Explanations

    options in lists

    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
    ४
    0.49
     fabricant
    0.46
    sulfanyl
    0.46
    ३
    0.45
    ५
    0.45
    fait
    0.45
    avion
    0.45
    එ
    0.45
    インストール
    0.44
    た
    0.44
    POSITIVE LOGITS
     подготовке
    0.48
     Borrower
    0.46
     Borough
    0.45
     Nomination
    0.44
     Bath
    0.43
     مشروع
    0.43
     Workers
    0.42
     گری
    0.41
     ప్రశ్
    0.41
     hemat
    0.41
    Activations Density 0.001%

    No Known Activations