© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9352
    Prev
    Next
    INDEX
    Explanations

    elite team performance and accolades

    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_22_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
     danh
    1.03
     giants
    0.99
     famosos
    0.98
     gurus
    0.97
     Gré
    0.91
    箴
    0.88
     знамени
    0.87
     prenda
    0.86
     canopy
    0.85
     blockbuster
    0.84
    POSITIVE LOGITS
    Clr
    1.03
    เก็บ
    0.83
    Computed
    0.83
     Computed
    0.80
    েরই
    0.80
    刎
    0.78
     লাশ
    0.78
    瘩
    0.76
     เก็บ
    0.76
    qrt
    0.74
    Activations Density 0.092%

    No Known Activations