© 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. 149732
    Prev
    Next
    INDEX
    Explanations

    geriatric

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

    for gaming dataset disease

    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
    ၊
    0.61
     buds
    0.47
     planks
    0.46
    чём
    0.46
     glands
    0.45
    、
    0.45
    ना
    0.45
     qué
    0.45
    it
    0.45
    亿
    0.45
    POSITIVE LOGITS
    HeaderParams
    0.47
    IsNull
    0.47
    Appending
    0.45
    ാര
    0.44
     उदासीन
    0.43
    Finder
    0.42
    Notifier
    0.42
    álního
    0.41
    FrameLayout
    0.40
     Padova
    0.40
    Activations Density 0.001%

    No Known Activations