© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69786
    Prev
    Next
    INDEX
    Explanations

    Fu followed by different words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    they
    -3.27
    c
    -2.81
    ly
    -2.66
    ve
    -2.59
    la
    -2.58
    {
    -2.55
    鬟
    -2.50
    a
    -2.47
    n
    -2.47
    le
    -2.44
    POSITIVE LOGITS
     IBRARY
    2.69
    镠
    2.67
    陛
    2.58
     According
    2.45
    rália
    2.41
     However
    2.38
    stücks
    2.31
     Because
    2.31
    ászló
    2.30
     don
    2.28
    Activations Density 0.005%

    No Known Activations