© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9941
    Prev
    Next
    INDEX
    Explanations

    as input

    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
    ided
    0.99
    IDING
    0.94
    払
    0.88
    쨩
    0.86
    んで
    0.84
     Worthing
    0.84
    anged
    0.83
    隼
    0.83
    ッティング
    0.82
    чко
    0.82
    POSITIVE LOGITS
     empresas
    1.24
     algún
    1.23
     dal
    1.18
     obras
    1.15
     campañas
    1.14
     gestión
    1.11
     ações
    1.10
     administração
    1.09
     firmy
    1.08
     firmas
    1.08
    Activations Density 0.018%

    No Known Activations