© 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. 7-GEMMASCOPE-2-RES-16K
    7. 2921
    Prev
    Next
    INDEX
    Explanations

    Why you're seeing

    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_7_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
    핵
    1.10
    국
    1.09
     lượng
    0.95
    કાર
    0.94
     পরবর্তী
    0.91
     hậu
    0.91
    ボディ
    0.91
     deriv
    0.90
    Bodies
    0.90
    м
    0.89
    POSITIVE LOGITS
    agaman
    1.05
    boleh
    1.05
    ے
    1.04
     ఆఫ్
    1.03
    राय
    1.02
    cana
    1.02
     صلى
    1.01
    hire
    1.00
    bygg
    0.99
    rometry
    0.99
    Activations Density 0.036%

    No Known Activations