© 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. 7-GEMMASCOPE-2-RES-16K
    7. 2291
    Prev
    Next
    INDEX
    Explanations

    python `__main__` guard

    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
    m
    2.12
     일이
    1.82
    mi
    1.82
    σου
    1.75
    ler
    1.74
    na
    1.68
     들
    1.65
    lers
    1.64
    트로
    1.64
    ming
    1.63
    POSITIVE LOGITS
    ಛ
    2.96
    Ско
    2.69
     Controlador
    2.66
     courbes
    2.60
     Vertex
    2.58
     rescu
    2.55
    iedo
    2.51
     предоставляет
    2.51
     contabil
    2.51
     Фор
    2.50
    Activations Density 0.001%

    No Known Activations