© 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. 109036
    Prev
    Next
    INDEX
    Explanations

    describing attributes and classifying entities

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

    sounds and pronunciation guidance

    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
    為了
    0.53
    🚔
    0.49
    Donc
    0.47
    Champions
    0.46
     decking
    0.46
    閎
    0.46
    pouring
    0.45
    ल्पन
    0.45
    culares
    0.45
    Scot
    0.45
    POSITIVE LOGITS
     {
    0.62
    5
    0.49
     identifies
    0.48
    a
    0.47
    8
    0.45
     С
    0.45
     Identify
    0.45
     was
    0.45
     is
    0.44
     phr
    0.44
    Activations Density 0.000%

    No Known Activations