© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2538
    Prev
    Next
    INDEX
    Explanations

    Ex words and pregnancy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     fromi
    0.92
     nuclé
    0.92
    ppa
    0.90
    ISHED
    0.89
    ipat
    0.86
    调度
    0.83
    rated
    0.83
     ū
    0.81
    atios
    0.81
    iasa
    0.81
    POSITIVE LOGITS
    引き続き
    1.26
    疣
    1.26
    ผ่านมา
    1.25
    顽
    1.25
     apreci
    1.21
    fetchall
    1.20
    ****************
    1.19
    捍
    1.18
     dụ
    1.18
    raquo
    1.18
    Activations Density 0.149%

    No Known Activations