© 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. 83192
    Prev
    Next
    INDEX
    Explanations

    sales, restaurant, diplomacy, money

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

    speed of sound, communication, scaling, competition

    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
    țial
    0.53
     영상을
    0.52
    <unused87>
    0.51
    <unused84>
    0.50
    بلی
    0.50
    cuno
    0.49
     नाबाल
    0.49
    ıkl
    0.48
    वेद
    0.48
     Omphalodes
    0.48
    POSITIVE LOGITS
    ’
    0.52
     loss
    0.47
     extensions
    0.47
     money
    0.46
     buying
    0.46
     understandable
    0.45
     windows
    0.45
     financier
    0.45
     Money
    0.44
     be
    0.44
    Activations Density 0.001%

    No Known Activations