© 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. 6598
    Prev
    Next
    INDEX
    Explanations

    programming functions

    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
    णे
    0.25
    юць
    0.24
    蟀
    0.24
    міст
    0.23
    料理
    0.23
    邊
    0.23
    味料
    0.23
    名单
    0.22
    мовір
    0.22
    CRIPTOR
    0.22
    POSITIVE LOGITS
     get
    0.67
     create
    0.61
    get
    0.61
     generate
    0.54
     make
    0.54
     calculate
    0.52
    generate
    0.51
    create
    0.50
     find
    0.49
    calculate
    0.49
    Activations Density 0.103%

    No Known Activations