© 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. 2112
    Prev
    Next
    INDEX
    Explanations

    and, plus, or connectors

    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
    reverse
    0.41
    print
    0.41
    github
    0.40
    google
    0.39
    using
    0.39
    docker
    0.38
    ocaly
    0.38
    ०
    0.37
    फ़
    0.37
    根据
    0.36
    POSITIVE LOGITS
     و
    0.60
     плюс
    0.59
     සහ
    0.56
     plus
    0.54
     અને
    0.53
     и
    0.52
     și
    0.51
     ਅਤੇ
    0.51
     ovviamente
    0.50
     và
    0.50
    Activations Density 0.361%

    No Known Activations