© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 19940
    Prev
    Next
    INDEX
    Explanations

    Football news and commentary

    np_acts-logits-general · gemini-2.5-flash-lite

    uvxyz variables

    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
    IconButton
    0.43
     formalin
    0.42
    ၈
    0.41
     autocl
    0.41
     Spectra
    0.40
     Schwar
    0.40
    িকর
    0.40
     Tric
    0.39
     cleverly
    0.39
    checkBox
    0.38
    POSITIVE LOGITS
     війни
    0.48
    👖
    0.44
     полити
    0.44
     жінок
    0.43
     удержи
    0.43
     втра
    0.43
     ვა
    0.43
    擄
    0.43
     жі
    0.42
     вій
    0.42
    Activations Density 0.000%

    No Known Activations