© 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-65K
    7. 40341
    Prev
    Next
    INDEX
    Explanations

    minimalist, medical device, open source

    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_65k_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
    बिया
    0.44
    కి
    0.43
    nyt
    0.41
    ivac
    0.41
    鰥
    0.40
     lung
    0.39
    IVING
    0.39
    spot
    0.39
    дать
    0.39
    udp
    0.38
    POSITIVE LOGITS
     replaced
    0.48
     сфере
    0.44
     дина
    0.44
     elegante
    0.43
    Straße
    0.42
     Congrès
    0.42
    Gruß
    0.41
    iegel
    0.41
     vatth
    0.41
    $('
    0.41
    Activations Density 0.011%

    No Known Activations