© 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. 11628
    Prev
    Next
    INDEX
    Explanations

    Would you rather

    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
    奘
    1.93
    asthen
    1.85
    rH
    1.79
    tif
    1.74
    s
    1.73
    <bos>
    1.65
     признаки
    1.63
    aries
    1.60
    ska
    1.59
    ói
    1.53
    POSITIVE LOGITS
    ٽ
    2.32
    ਟ
    2.26
    ค์
    2.24
    臾
    2.22
    zenia
    2.21
    Χ
    2.18
    ЕНИ
    2.15
     constexpr
    2.15
    박
    2.14
    desa
    2.11
    Activations Density 0.048%

    No Known Activations