© 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. 103451
    Prev
    Next
    INDEX
    Explanations

    null

    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
    了不少
    -1.47
     が
    -1.44
    Without
    -1.44
     这
    -1.44
     But
    -1.43
    f
    -1.43
     That
    -1.41
     niečo
    -1.40
     člov
    -1.39
     možno
    -1.38
    POSITIVE LOGITS
    \
    1.83
    หรือ
    1.72
     its
    1.66
     imó
    1.54
    OrNull
    1.51
     Autó
    1.46
     jego
    1.42
     teras
    1.42
     this
    1.41
    prende
    1.41
    Activations Density 0.023%

    No Known Activations