© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 68955
    Prev
    Next
    INDEX
    Explanations

    telemetry, asString, xffffff, hasData, telehealth

    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
     Then
    -3.36
    lossians
    -2.84
    蹰
    -2.61
     actitud
    -2.53
    vantaged
    -2.53
     כך
    -2.50
    𝄆
    -2.48
    灩
    -2.44
     alors
    -2.44
     femenino
    -2.42
    POSITIVE LOGITS
    I
    3.67
    i
    3.67
    </strong>
    3.52
    <i>
    3.50
    *
    3.48
    the
    3.14
    <
    3.11
    an
    3.00
     ‘
    2.97
      
    2.92
    Activations Density 0.010%

    No Known Activations