© 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. 7-GEMMASCOPE-2-RES-16K
    7. 290
    Prev
    Next
    INDEX
    Explanations

    `for` loops and mathematical variables

    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_7_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
    י
    3.32
    ا
    3.25
    加坡
    3.23
    ০
    3.10
    ೆ
    2.96
    e
    2.95
    ে
    2.94
    y
    2.93
    ಿ
    2.87
    る
    2.86
    POSITIVE LOGITS
    Д
    1.66
    äl
    1.64
    Г
    1.63
    oth
    1.63
    La
    1.63
    #
    1.60
    (
    1.58
    als
    1.56
    ules
    1.54
    ista
    1.53
    Activations Density 0.407%

    No Known Activations