© 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. 6207
    Prev
    Next
    INDEX
    Explanations

    Matthew, matt, mattress, matplotlib

    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
    나
    1.36
    arı
    1.23
     a
    1.15
    на
    1.14
    다
    1.12
    ون
    1.10
    ,
    1.09
    ଈ
    1.08
    ა
    1.05
    nia
    1.05
    POSITIVE LOGITS
    ن
    1.52
    re
    1.25
    f
    1.22
    خ
    1.19
     for
    1.15
    、
    1.15
    n
    1.03
    ז
    1.00
    ص
    0.99
    z
    0.98
    Activations Density 0.059%

    No Known Activations