© 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. 7489
    Prev
    Next
    INDEX
    Explanations

    FizzBuzz conditional logic

    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
    㳒
    1.28
     アンティーク
    1.21
     INTEGER
    1.18
     除了
    1.15
     क्लब
    1.14
    哠
    1.14
    哃
    1.13
     PREVENTION
    1.11
     trabajo
    1.10
    穵
    1.10
    POSITIVE LOGITS
    <h2>
    1.00
    F
    0.89
    Ab
    0.89
    adir
    0.87
    Ad
    0.87
     Beal
    0.85
    BC
    0.84
    ”,
    0.84
    <h3>
    0.84
    Th
    0.83
    Activations Density 0.003%

    No Known Activations