© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 250716
    Prev
    Next
    INDEX
    Explanations

    package followed by a noun or verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    pai
    0.49
    atho
    0.47
    apay
    0.47
    emptive
    0.46
    ari
    0.46
    붉
    0.44
    rim
    0.44
    =>{
    0.44
    red
    0.43
    (':')[
    0.43
    POSITIVE LOGITS
    是
    0.60
    ز
    0.59
    是對
    0.52
    は
    0.51
    是他
    0.48
    gleichen
    0.48
     кажется
    0.47
    谊
    0.47
    มัน
    0.46
    浮か
    0.46
    Activations Density 0.001%

    No Known Activations