© 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. 203301
    Prev
    Next
    INDEX
    Explanations

    Venice Biennales, safety instructions, medical conditions

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

    assess and explain problems

    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
    an
    0.60
    to
    0.55
    as
    0.53
    in
    0.50
    ាំង
    0.50
    et
    0.49
    n
    0.48
     to
    0.48
    t
    0.48
    a
    0.46
    POSITIVE LOGITS
    RecyclerView
    0.55
    ArrayAdapter
    0.48
     Conselho
    0.48
    ឧប
    0.47
    yclerView
    0.46
    HttpSession
    0.44
    อาการ
    0.44
     ആശയ
    0.44
    WindowEvent
    0.44
    RestController
    0.43
    Activations Density 0.003%

    No Known Activations