© 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. 67122
    Prev
    Next
    INDEX
    Explanations

    money, comfortable, specific entities

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

    while X, Y comparison

    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
    CCCc
    0.46
    nSamples
    0.46
    ClickListener
    0.42
    Eta
    0.41
    ChessBot
    0.41
     tassels
    0.41
    幸
    0.41
    achelor
    0.40
    Eigen
    0.39
     déco
    0.39
    POSITIVE LOGITS
     criticised
    0.51
     THE
    0.50
     OUR
    0.48
     C
    0.48
     are
    0.47
     F
    0.47
     derived
    0.46
     DEN
    0.46
    İ
    0.45
    而非
    0.45
    Activations Density 0.002%

    No Known Activations