© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14553
    Prev
    Next
    INDEX
    Explanations

    defines or declares functions and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     Prep
    0.81
    丫
    0.78
    一本
    0.76
     finalized
    0.74
    isha
    0.73
    เศ
    0.73
     elabor
    0.71
     prep
    0.71
     unresolved
    0.71
     virg
    0.70
    POSITIVE LOGITS
     selber
    1.22
     overseeing
    1.21
     ഓഫീ
    1.21
    獧
    1.19
     mediators
    1.19
     برج
    1.19
     Offices
    1.16
     Salaries
    1.15
     විසින්
    1.15
    StaticHandler
    1.15
    Activations Density 0.209%

    No Known Activations