© 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. 10551
    Prev
    Next
    INDEX
    Explanations

    observable universe

    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>
    3.10
     duro
    3.04
     certainement
    2.79
    attribution
    2.71
    engi
    2.64
    筊
    2.63
    ાળ
    2.62
     accurate
    2.58
    ⢸
    2.56
    esin
    2.55
    POSITIVE LOGITS
    AnimationFrame
    2.92
    s
    2.63
    ी
    2.59
    sia
    2.48
    af
    2.47
    z
    2.37
    তাপ
    2.31
     مرور
    2.30
    QRST
    2.27
    hers
    2.26
    Activations Density 0.002%

    No Known Activations