© 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. 34-GEMMASCOPE-RES-131K
    7. 58628
    Prev
    Next
    INDEX
    Explanations

    sensor readings and device data

    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_34/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
    SearchResults
    -0.96
     œil
    -0.90
    Natur
    -0.88
    lucene
    -0.81
     作業
    -0.79
    hoten
    -0.79
    gameId
    -0.77
    rechnung
    -0.77
    নে
    -0.77
     LDAP
    -0.76
    POSITIVE LOGITS
     sensor
    2.78
     sensors
    2.58
    sensor
    2.17
     readings
    2.13
     Sensor
    2.11
     temperature
    1.91
    Sensor
    1.91
     measurements
    1.80
     measurement
    1.74
     device
    1.67
    Activations Density 0.056%

    No Known Activations