© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 123865
    Prev
    Next
    INDEX
    Explanations

    want to, like

    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
     you
    -2.27
    {
    -2.00
    ’
    -1.82
     usado
    -1.77
     versucht
    -1.75
    但她
    -1.73
    って何
    -1.73
     referenced
    -1.67
     lanza
    -1.59
    のおすすめ
    -1.59
    POSITIVE LOGITS
    ≧
    1.48
    ът
    1.47
    We
    1.42
    🍕
    1.41
    бою
    1.41
    мый
    1.40
     HttpNotFound
    1.38
    jning
    1.37
    THX
    1.36
     monotony
    1.36
    Activations Density 0.013%

    No Known Activations