© 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. 57234
    Prev
    Next
    INDEX
    Explanations

    Marine geophysical

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on numeric measurements (temperatures, wind speeds, percentages, times, etc.) as they appear in weather-report style data.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     върху
    -0.82
     abierta
    -0.77
     oświet
    -0.76
    ときは
    -0.75
     épo
    -0.74
    pendicular
    -0.73
     Bedürfn
    -0.72
     états
    -0.71
     عبر
    -0.69
    bieg
    -0.69
    POSITIVE LOGITS
    becoming
    1.00
     continued
    0.94
     Increasing
    0.93
     Becoming
    0.92
    increasing
    0.91
     forecast
    0.86
     Slightly
    0.85
    Possible
    0.85
     becoming
    0.85
    ichten
    0.84
    Activations Density 0.024%

    No Known Activations