© 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. 100077
    Prev
    Next
    INDEX
    Explanations

    programming definitions and concepts

    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
     Speicher
    0.47
    儲
    0.47
    wards
    0.46
    byshire
    0.44
     underground
    0.43
    ymmet
    0.43
    ividade
    0.42
     развед
    0.42
    ové
    0.42
    вала
    0.41
    POSITIVE LOGITS
    ریح
    0.49
    عی
    0.47
     casework
    0.47
    侯
    0.47
    获奖
    0.46
    곸
    0.46
    নিজ
    0.44
     caseworker
    0.44
    ฝึก
    0.44
     KIND
    0.42
    Activations Density 0.002%

    No Known Activations