© 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. 40-GEMMASCOPE-2-RES-262K
    7. 84708
    Prev
    Next
    INDEX
    Explanations

    math.sqrt, Math.pow

    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_40_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
    觎
    0.41
    🙊
    0.38
    chalk
    0.38
    👲
    0.38
    joining
    0.37
    ーリー
    0.37
    윳
    0.37
    쳐
    0.37
    モンスター
    0.37
    講
    0.37
    POSITIVE LOGITS
    भाग्य
    0.42
     ঘৃণা
    0.40
     slider
    0.39
     بالأ
    0.38
     engra
    0.38
     multil
    0.38
     riguard
    0.37
     editor
    0.36
     بالس
    0.36
     highest
    0.36
    Activations Density 0.001%

    No Known Activations