© 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. 5098
    Prev
    Next
    INDEX
    Explanations

    zero or percentages

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

    zero

    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
    十五
    0.47
    իտ
    0.46
    十二
    0.43
    ၆
    0.43
    十六
    0.42
    ๙
    0.42
    十八
    0.41
    ၈
    0.41
    ૬
    0.40
    ၉
    0.40
    POSITIVE LOGITS
    ₀
    0.74
    𝟬
    0.72
    0
    0.69
    ０
    0.66
    ٠
    0.66
    𝟎
    0.66
    ᱐
    0.64
    ০
    0.61
    ೦
    0.59
    ۰
    0.58
    Activations Density 0.288%

    No Known Activations