© 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. 22088
    Prev
    Next
    INDEX
    Explanations

    facilities and context

    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
    ௅
    -1.80
    sätzlich
    -1.80
    一般的
    -1.67
    妧
    -1.63
     protože
    -1.63
     algemene
    -1.62
     verzame
    -1.59
    泔
    -1.58
    ocidade
    -1.57
     pomá
    -1.55
    POSITIVE LOGITS
    ↵↵
    2.14
    {
    2.03
     dieser
    1.73
    我们可以
    1.67
    sc
    1.67
     erne
    1.66
    >
    1.64
    也
    1.63
    this
    1.63
    k
    1.60
    Activations Density 0.020%

    No Known Activations