© 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. 99957
    Prev
    Next
    INDEX
    Explanations

    awaiting further action or approval

    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
    .
    -2.25
    {
    -1.84
    ти
    -1.78
     It
    -1.73
    _
    -1.65
     \
    -1.65
    ⼼
    -1.62
     "../../../../
    -1.59
     Eighty
    -1.55
     In
    -1.54
    POSITIVE LOGITS
     dekoratif
    1.78
     berikan
    1.76
    i
    1.73
    IFESTYLE
    1.71
    此前
    1.69
     którzy
    1.68
    髎
    1.67
    𞤢
    1.65
     inim
    1.64
    現在は
    1.64
    Activations Density 0.002%

    No Known Activations