© 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. 172601
    Prev
    Next
    INDEX
    Explanations

    at

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

    if you

    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
     desk
    0.48
     desks
    0.47
    ↵
    0.44
     drawbacks
    0.43
    พัฒ
    0.43
    这些
    0.43
     medals
    0.42
    某些
    0.42
     bras
    0.42
    太多
    0.42
    POSITIVE LOGITS
    俻
    0.50
     будет
    0.50
     bebida
    0.50
     совер
    0.48
     уничто
    0.48
    啠
    0.48
     fooling
    0.47
    㖡
    0.47
    emitting
    0.47
     выполняется
    0.46
    Activations Density 0.002%

    No Known Activations