© 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. 15522
    Prev
    Next
    INDEX
    Explanations

    code execution and differences

    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
    蔫
    0.46
    nungs
    0.44
    ズニー
    0.41
     güneş
    0.39
    蕤
    0.39
     hangat
    0.38
    ynu
    0.38
    ினார்கள்
    0.38
    腆
    0.38
    वारी
    0.38
    POSITIVE LOGITS
     Bengali
    0.40
    ansu
    0.40
     Tamil
    0.38
     autonom
    0.36
     meme
    0.35
     uniq
    0.35
    [
    0.35
     AN
    0.34
     Khmer
    0.34
     sv
    0.33
    Activations Density 0.000%

    No Known Activations