© 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. 9659
    Prev
    Next
    INDEX
    Explanations

    lean protein

    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
    鎿
    0.46
    波动
    0.46
    響
    0.45
    アクション
    0.45
    Introduction
    0.44
    を探
    0.44
     paddles
    0.43
    발
    0.43
    湫
    0.42
    χει
    0.42
    POSITIVE LOGITS
     sorgen
    0.47
     contradict
    0.47
     comest
    0.45
    defn
    0.44
     benz
    0.44
     shareholder
    0.44
     incre
    0.43
    ové
    0.43
    ová
    0.42
     Zagreb
    0.42
    Activations Density 0.004%

    No Known Activations