© 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. 16-GEMMASCOPE-2-RES-262K
    7. 3269
    Prev
    Next
    INDEX
    Explanations

    smoothness in performance and process

    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_16_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
    1.15
    is
    1.12
    SI
    1.03
    ni
    1.02
    ation
    0.96
    k
    0.94
    DI
    0.90
    ’
    0.89
    ner
    0.88
    es
    0.87
    POSITIVE LOGITS
    ו
    1.30
    ل
    1.25
    smooth
    1.19
     smoothness
    1.19
    و
    1.18
     smooth
    1.13
     smoother
    1.12
    р
    1.10
     smoothed
    1.09
    ל
    1.09
    Activations Density 0.024%

    No Known Activations