© 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. 13-GEMMASCOPE-2-RES-65K
    4. 1764
    Prev
    Next
    INDEX
    Explanations

    Chinese or Brazilian market

    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
    ccia
    1.23
     anger
    1.10
    𝚗
    1.09
    ্প
    1.08
    cter
    1.01
     initial
    1.00
    aga
    1.00
    chaft
    1.00
     ஆணைய
    0.99
    axiom
    0.99
    POSITIVE LOGITS
    ات
    1.60
    tive
    1.54
     ภาษา
    1.47
    Су
    1.44
    s
    1.43
    了
    1.39
    ्स
    1.36
    Wrapped
    1.36
    This
    1.36
    Straw
    1.35
    Activations Density 0.001%

    No Known Activations