© 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. 25537
    Prev
    Next
    INDEX
    Explanations

    South Carolina national action location

    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
     classiques
    0.46
     쉬
    0.45
    PAY
    0.45
     शक्तिशाली
    0.44
     principales
    0.43
     gleichen
    0.43
    TouchUpInside
    0.43
     लाग
    0.42
     usia
    0.42
     අපි
    0.42
    POSITIVE LOGITS
    )--(
    0.46
    Ｄ
    0.45
    idently
    0.43
    忆
    0.42
     Mens
    0.42
    一段
    0.42
     Bitter
    0.42
     exer
    0.41
     distin
    0.41
    他人
    0.40
    Activations Density 0.005%

    No Known Activations