© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 815
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and calculations

    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
    ,
    1.23
     and
    1.21
     phased
    1.19
     from
    1.14
     victims
    1.10
     at
    1.10
     ap
    1.10
     am
    1.07
     Masters
    1.07
     flash
    1.07
    POSITIVE LOGITS
    Denominator
    1.69
     TInner
    1.59
    BinaryOperation
    1.57
    UnaryOperation
    1.57
    infini
    1.54
    Ẻ
    1.54
    denominator
    1.52
     convirtió
    1.48
    Entropy
    1.47
     परिमेय
    1.46
    Activations Density 0.114%

    No Known Activations