© 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. 109719
    Prev
    Next
    INDEX
    Explanations

    unless specifically

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

    foreign language or specialized terms

    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
    \
    0.48
    <>
    0.47
     dien
    0.44
     likewise
    0.42
     sown
    0.42
    [
    0.42
     evergreen
    0.41
    istent
    0.40
     interpret
    0.40
    Your
    0.40
    POSITIVE LOGITS
    璋
    0.45
     तकलीफ
    0.44
    ция
    0.43
    拍
    0.43
    鐒
    0.43
    ารถ
    0.43
    спользование
    0.43
    发现
    0.42
    қу
    0.42
    發現
    0.42
    Activations Density 0.000%

    No Known Activations