© 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. 193483
    Prev
    Next
    INDEX
    Explanations

    non-latin word endings

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

    not like throwing

    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
    lr
    0.59
     hao
    0.49
     (
    0.47
     results
    0.47
    S
    0.47
    rl
    0.46
    lada
    0.46
    l
    0.46
    lir
    0.46
    rh
    0.45
    POSITIVE LOGITS
    ேச
    0.54
     память
    0.48
     Technologien
    0.48
    勍
    0.48
    ين
    0.47
    ছিলাম
    0.47
    நாத
    0.45
     письмо
    0.45
     значительно
    0.45
     kapcsol
    0.45
    Activations Density 0.001%

    No Known Activations