© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3650
    Prev
    Next
    INDEX
    Explanations

    claim or threat

    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
    <bos>
    3.16
    ৗ
    2.77
    ه
    2.68
    javax
    2.63
    ़
    2.62
    ύ
    2.52
    ী
    2.49
    结
    2.49
    inggi
    2.48
     BufferedWriter
    2.47
    POSITIVE LOGITS
    ming
    4.08
    dır
    3.60
    mies
    3.49
    mes
    3.40
    พ์
    3.38
    mi
    3.35
    mie
    3.33
    mers
    3.30
    ্বল
    3.24
    ป์
    3.20
    Activations Density 0.386%

    No Known Activations