© 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. 676
    Prev
    Next
    INDEX
    Explanations

    Westcott and Text Line

    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
    اتها
    0.80
    ŧ
    0.77
     sentencia
    0.77
    يتي
    0.76
     ImageData
    0.76
    etrotters
    0.75
    NotNull
    0.74
    썰
    0.71
    쥘
    0.70
    وق
    0.70
    POSITIVE LOGITS
    ERN
    1.31
     Africa
    1.27
    側の
    1.25
    side
    1.23
    wards
    1.22
    ward
    1.21
     carolina
    1.15
     African
    1.14
    west
    1.14
     africa
    1.13
    Activations Density 0.817%

    No Known Activations