© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 84699
    Prev
    Next
    INDEX
    Explanations

    API company games keywords

    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
    URUK
    0.45
    ٤
    0.44
    的首
    0.43
     材料
    0.43
    eosin
    0.42
    IBC
    0.41
    ثم
    0.41
    的模型
    0.41
    ͎
    0.41
    жного
    0.41
    POSITIVE LOGITS
     você
    0.58
     you
    0.52
     bạn
    0.49
     everyone
    0.48
     homeschooling
    0.48
     તમારે
    0.47
     exhilar
    0.46
     acabar
    0.46
    రోజు
    0.46
     অবশেষে
    0.45
    Activations Density 0.012%

    No Known Activations