© 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. 7-GEMMASCOPE-2-RES-16K
    7. 12396
    Prev
    Next
    INDEX
    Explanations

    สวัสดีวัด

    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
    Ẩ
    3.19
    prav
    2.93
    lı
    2.92
    𝘵
    2.92
    ança
    2.91
    gın
    2.90
    น้อง
    2.88
    cé
    2.86
    此之外
    2.85
    cule
    2.85
    POSITIVE LOGITS
    res
    2.14
    ிற்கு
    2.11
    й
    2.11
     m
    2.10
    urne
    1.95
    ру
    1.89
    >>()
    1.81
    inert
    1.80
     tal
    1.76
    িকল্প
    1.71
    Activations Density 0.002%

    No Known Activations