© 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
    2. Gemma-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 9415
    Prev
    Next
    INDEX
    Explanations

    public data types

    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
     Beng
    1.05
     Bers
    1.04
     θ
    0.95
     Λ
    0.92
     Arabia
    0.90
     Arabs
    0.90
     Lumin
    0.87
     NH
    0.86
     Town
    0.84
     PN
    0.84
    POSITIVE LOGITS
    Accessed
    0.98
    Ashley
    0.95
     n
    0.91
     verrez
    0.90
    nsan
    0.90
    Estate
    0.90
     Stacey
    0.90
    Spencer
    0.90
    สด
    0.89
    Joshua
    0.89
    Activations Density 0.028%

    No Known Activations