© 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. 84650
    Prev
    Next
    INDEX
    Explanations

    love and cost

    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
    တယ်
    0.41
     القسمه
    0.40
    𒁀
    0.39
    emaakt
    0.38
    liegen
    0.37
     braking
    0.37
     paroi
    0.37
    тому
    0.37
     réf
    0.37
     पेट्रोलियम
    0.36
    POSITIVE LOGITS
     नव
    0.43
    sentence
    0.39
    Episodes
    0.38
    Function
    0.38
    Pages
    0.36
    ūn
    0.36
    加
    0.35
    支撑
    0.35
    fet
    0.34
    mixed
    0.34
    Activations Density 0.000%

    No Known Activations