© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59000
    Prev
    Next
    INDEX
    Explanations

    CEST, JULY, CentOS, CERN

    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
     to
    -2.77
    応え
    -2.53
    medriver
    -2.45
    弍
    -2.39
    狆
    -2.38
     “[
    -2.34
    啸
    -2.33
    ⾏
    -2.30
    咎
    -2.23
    📏
    -2.23
    POSITIVE LOGITS
    {
    3.39
     the
    3.09
    of
    3.02
    うわ
    2.72
    2
    2.69
    l
    2.56
    最初の
    2.48
    ありがたい
    2.47
     harten
    2.45
    4
    2.41
    Activations Density 0.001%

    No Known Activations