© 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. 34-GEMMASCOPE-RES-131K
    7. 106964
    Prev
    Next
    INDEX
    Explanations

    magnetic sensors

    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
     Gerichts
    -0.76
    addis
    -0.72
    volmente
    -0.71
    ペラ
    -0.69
    Friedrich
    -0.69
    YECTO
    -0.68
     grind
    -0.68
     emit
    -0.67
     radar
    -0.66
     Lamps
    -0.66
    POSITIVE LOGITS
     SQU
    0.96
    helmet
    0.91
     Sensor
    0.88
    Sensor
    0.85
    sensor
    0.84
    эффици
    0.82
     sensor
    0.82
     JPanel
    0.81
    Assemb
    0.79
     JsonObject
    0.79
    Activations Density 0.028%

    No Known Activations