© 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. 13-GEMMASCOPE-2-RES-65K
    7. 1661
    Prev
    Next
    INDEX
    Explanations

    account ownership

    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_65k_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
     do
    0.98
     our
    0.94
     +
    0.93
    erv
    0.90
    ools
    0.86
     (
    0.86
    wa
    0.86
    our
    0.84
    kunde
    0.83
     ∈
    0.80
    POSITIVE LOGITS
     declaraciones
    2.11
     declaró
    2.06
     portavoz
    2.00
     afirmó
    1.98
     criticizing
    1.97
     spokesman
    1.96
     말했다
    1.96
     expresó
    1.95
     condemning
    1.94
     remarks
    1.94
    Activations Density 0.477%

    No Known Activations