© 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. 11149
    Prev
    Next
    INDEX
    Explanations

    gravity as curvature of spacetime

    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
    undum
    1.85
    enu
    1.78
    table
    1.71
    äts
    1.65
    ़
    1.64
    und
    1.63
    ü
    1.63
    дің
    1.62
    esh
    1.61
    できるように
    1.61
    POSITIVE LOGITS
    artney
    2.68
    淒
    2.54
     lĩnh
    2.50
     thủy
    2.47
     Chiến
    2.45
    ㄡ
    2.45
    𝘥
    2.41
    楂
    2.40
    PARTMENT
    2.40
    Qnt
    2.39
    Activations Density 0.034%

    No Known Activations