© 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. 17483
    Prev
    Next
    INDEX
    Explanations

    Sig or sigma variations

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

    Six Sigma, sigmoid, σ

    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
    ꯔ
    0.42
     Xuan
    0.42
    یین
    0.41
     Potato
    0.39
     fantasia
    0.39
     Missile
    0.39
     খো
    0.38
    FANG
    0.38
    玥
    0.38
     Jade
    0.37
    POSITIVE LOGITS
     SIG
    3.97
     sigma
    3.91
     Sig
    3.89
    Sig
    3.88
     sig
    3.83
    SIG
    3.77
    sigma
    3.70
     Sigma
    3.63
    sig
    3.61
     σ
    3.33
    Activations Density 0.047%

    No Known Activations