© 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. 7765
    Prev
    Next
    INDEX
    Explanations

    standard deviation

    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
     आरमार
    0.48
    蓖
    0.48
    柰
    0.47
    篦
    0.46
    
    0.45
     приорите
    0.44
     collegamento
    0.44
     অগ্রাধিকার
    0.44
    货币
    0.43
    二进制
    0.43
    POSITIVE LOGITS
     variance
    1.51
    Variance
    1.38
     Variance
    1.35
     variances
    1.30
    variance
    1.27
     mean
    1.16
     Gaussian
    1.16
     sigma
    1.14
     σ
    1.06
    sigma
    1.05
    Activations Density 0.088%

    No Known Activations