© 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. 31-GEMMASCOPE-2-RES-262K
    7. 57186
    Prev
    Next
    INDEX
    Explanations

    multiplication or scaling

    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_31_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
    㕣
    0.47
     মধ্যকার
    0.46
     بين
    0.43
    ላለ
    0.41
    狛
    0.41
    illance
    0.40
     =[
    0.40
    槸
    0.40
     अम्ब
    0.39
    潵
    0.39
    POSITIVE LOGITS
     entusiasmo
    0.49
     kepala
    0.47
     rapidamente
    0.46
     perfe
    0.46
     juventud
    0.45
     asal
    0.43
     impressively
    0.43
     poise
    0.43
     entusias
    0.43
     impul
    0.42
    Activations Density 0.003%

    No Known Activations