© 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. 31-GEMMASCOPE-2-RES-262K
    7. 28765
    Prev
    Next
    INDEX
    Explanations

    cars, lectures, and icons

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

    comparing and contrasting

    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_31_width_262k_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
    UpperCase
    0.50
     等
    0.50
     veines
    0.50
    ITA
    0.48
    Chemistry
    0.48
    IntValue
    0.48
    Enumer
    0.47
     来
    0.47
    ATO
    0.46
    o
    0.46
    POSITIVE LOGITS
     stunning
    0.50
     iconic
    0.48
    ستخدم
    0.47
     गाडी
    0.45
     beloved
    0.44
    ếc
    0.44
     lighting
    0.44
    грева
    0.44
     lecture
    0.43
     त्याला
    0.43
    Activations Density 0.000%

    No Known Activations