© 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. 14152
    Prev
    Next
    INDEX
    Explanations

    depreciation expense and probability distributions

    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
    嗌
    2.09
     rang
    1.91
     cad
    1.87
     tho
    1.77
     mob
    1.74
    inien
    1.70
    בה
    1.69
    ró
    1.68
    IO
    1.67
    v
    1.66
    POSITIVE LOGITS
    的反
    2.34
    ของ
    2.27
    Of
    2.25
    َة
    2.18
    ណ៍
    2.14
    Disclosure
    2.07
    ׁ
    2.06
    َت
    2.04
    ened
    2.02
    মাদের
    2.01
    Activations Density 0.000%

    No Known Activations