© 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. 110747
    Prev
    Next
    INDEX
    Explanations

    SELECT, Makefile, Orange

    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
    ܀
    0.43
    turns
    0.43
    upa
    0.43
     smack
    0.41
    owed
    0.41
    upas
    0.41
     عوض
    0.39
    paired
    0.38
    degrees
    0.37
    ندر
    0.37
    POSITIVE LOGITS
     Orange
    0.39
    钤
    0.39
     Makefile
    0.39
    鄢
    0.38
     اضافه
    0.37
     दिलीप
    0.37
     Sunil
    0.37
     ваго
    0.37
     usize
    0.37
     базе
    0.37
    Activations Density 0.001%

    No Known Activations