© 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. 189012
    Prev
    Next
    INDEX
    Explanations

    highest rated

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

    non-English word parts

    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
     heads
    0.54
    ↵
    0.52
     str
    0.52
     shape
    0.52
     commander
    0.50
    €™
    0.50
     five
    0.49
    identity
    0.49
     x
    0.48
     পাঁচটি
    0.48
    POSITIVE LOGITS
    ной
    0.68
    㐰
    0.54
    ці
    0.54
    лі
    0.53
    чках
    0.52
    ното
    0.52
    百貨
    0.52
    слі
    0.51
    лева
    0.51
    лах
    0.50
    Activations Density 0.000%

    No Known Activations