© 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. 13-GEMMASCOPE-2-RES-16K
    7. 10617
    Prev
    Next
    INDEX
    Explanations

    asynchronous, Greek, rare, atomic

    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_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
    甶
    1.90
    setRequest
    1.83
    sam
    1.82
    韋
    1.81
    컥
    1.78
    urnal
    1.77
    igat
    1.74
     jah
    1.72
    сто
    1.69
    trn
    1.68
    POSITIVE LOGITS
    Γ
    2.37
     Γ
    2.21
    Athens
    2.18
    Greek
    2.07
     λ
    2.04
     Λ
    2.02
     ε
    1.98
     Θ
    1.95
     Athens
    1.86
    γ
    1.85
    Activations Density 0.948%

    No Known Activations