© 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. 57318
    Prev
    Next
    INDEX
    Explanations

    detecting or measuring light/signals

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

    This neuron fires strongly on language describing quantitative measurement or detection processes—e.g. mentions of detecting, measuring, assessing signals or 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
    distribute
    -0.84
    rall
    -0.79
    istert
    -0.77
     ganado
    -0.77
    distributor
    -0.76
    مرار
    -0.76
    قليم
    -0.74
    bentar
    -0.74
     uusi
    -0.73
    pstead
    -0.73
    POSITIVE LOGITS
     detector
    2.88
     detectors
    2.72
     detection
    2.63
     Detection
    2.23
    detector
    2.20
     Detector
    2.17
    Detector
    2.17
    Detection
    2.14
     detecting
    2.09
    detection
    2.06
    Activations Density 0.120%

    No Known Activations