© 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. 155215
    Prev
    Next
    INDEX
    Explanations

    purpose or relation

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

    part of or side of

    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
     Tough
    0.39
     Night
    0.38
     Kashmir
    0.38
     (
    0.38
     Buster
    0.38
     tận
    0.37
     nhân
    0.36
     Nhân
    0.36
     quicker
    0.36
     Breck
    0.36
    POSITIVE LOGITS
    DialogWhen
    0.54
    "]')
    0.50
    䇢
    0.50
    ≋
    0.50
     で
    0.50
     treatises
    0.50
     εται
    0.49
     έτσι
    0.49
     いき
    0.48
    Lorsque
    0.48
    Activations Density 0.003%

    No Known Activations