© 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. 5101
    Prev
    Next
    INDEX
    Explanations

    p-values and sample sizes

    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
     -$
    0.56
     !",
    0.55
     !_
    0.54
     ?-
    0.54
     Ã
    0.52
     Â
    0.52
     '/
    0.52
     -(
    0.52
     -"
    0.51
     ..............
    0.51
    POSITIVE LOGITS
    ՝
    0.79
    ．
    0.74
    ㆍ
    0.70
    ／
    0.68
    ‏:‏
    0.66
    ‐
    0.64
    ）（
    0.62
    ‌است
    0.61
    ＝＝
    0.60
    ﹣
    0.59
    Activations Density 0.142%

    No Known Activations