© 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. 74725
    Prev
    Next
    INDEX
    Explanations

    this is

    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
     and
    -1.81
    datable
    -1.59
     of
    -1.53
    äldrar
    -1.51
     zarówno
    -1.51
     также
    -1.48
    ϋ
    -1.45
    龊
    -1.41
    uliert
    -1.40
     också
    -1.38
    POSITIVE LOGITS
     or
    1.88
    or
    1.80
     due
    1.56
     so
    1.55
    ệu
    1.53
     they
    1.52
     it
    1.40
     to
    1.35
    だったので
    1.34
     the
    1.31
    Activations Density 0.253%

    No Known Activations