© 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. 65057
    Prev
    Next
    INDEX
    Explanations

    paste your input

    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
    servic
    0.48
    tra
    0.46
    isbn
    0.46
    grou
    0.46
     環
    0.45
    packageName
    0.45
     powertrain
    0.45
     g
    0.44
     geoLocation
    0.44
    label
    0.43
    POSITIVE LOGITS
    等方面
    0.49
    ਨ
    0.49
    හ
    0.48
    ント
    0.47
    ون
    0.46
    ના
    0.46
    まだ
    0.45
    序
    0.45
    вото
    0.45
    یر
    0.44
    Activations Density 0.003%

    No Known Activations