© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9843
    Prev
    Next
    INDEX
    Explanations

    file extension and format

    np_acts-logits-general · gemini-2.5-flash-lite

    file extension

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    щей
    0.40
    前进
    0.40
    egen
    0.39
     प्रतिक
    0.38
    積
    0.38
    カタ
    0.38
    🗝
    0.37
    odenal
    0.36
    ̅
    0.36
    uum
    0.35
    POSITIVE LOGITS
     extension
    1.20
     extensions
    1.19
     Extension
    1.17
    extension
    1.15
    Extension
    1.09
     Extensions
    1.09
    getExtension
    1.08
    EXTENSION
    1.06
    extensions
    1.05
    后缀
    1.05
    Activations Density 0.112%

    No Known Activations