© 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. 58560
    Prev
    Next
    INDEX
    Explanations

    experimental light splitting

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

    The neuron activates strongly on numeric measurements and units (e.g., values with associated scientific or engineering units).

    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
    Jeśli
    -0.80
     duvar
    -0.78
     علیه
    -0.77
    一天
    -0.76
    壁
    -0.75
    ceira
    -0.72
    بحث
    -0.72
    ICI
    -0.71
     kort
    -0.71
    WALL
    -0.70
    POSITIVE LOGITS
     Keith
    0.90
     measured
    0.82
    measured
    0.81
    Keith
    0.81
     bias
    0.81
     пробе
    0.79
    Bias
    0.79
     estimated
    0.77
    measurement
    0.77
     Device
    0.75
    Activations Density 0.063%

    No Known Activations