© 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. 136375
    Prev
    Next
    INDEX
    Explanations

    overview of sections

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

    . or of after certain words

    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
     arrang
    0.48
    sher
    0.48
    ellington
    0.47
     بى
    0.47
     bouquets
    0.46
    ($
    0.46
     adequ
    0.45
     compartments
    0.45
     ballon
    0.45
     discharges
    0.45
    POSITIVE LOGITS
    версите
    0.52
    elernt
    0.45
     Mục
    0.45
    возможно
    0.45
     Senate
    0.45
     Slack
    0.44
     Rune
    0.43
     [+]
    0.42
    好吧
    0.42
    ௦
    0.42
    Activations Density 0.001%

    No Known Activations