© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8034
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    np_acts-logits-general · gemini-2.5-flash-lite

    ordinal dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reporter
    0.41
    [
    0.40
    <strong>
    0.40
     ইচ্ছে
    0.39
    年
    0.39
    年至
    0.38
    ,
    0.38
    fmt
    0.38
     Centuries
    0.38
    (
    0.38
    POSITIVE LOGITS
     }{}_{\
    0.46
    Segments
    0.42
     depan
    0.42
     ነገር
    0.40
     segmentation
    0.39
    ዋል።
    0.39
     odors
    0.39
     segments
    0.38
    ೇನೆ
    0.38
    ご注意
    0.38
    Activations Density 0.045%

    No Known Activations