© 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. 62908
    Prev
    Next
    INDEX
    Explanations

    ceiling canopy mounting

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

    The neuron activates on technical specification lines containing numbers, units, and measurements (e.g., dimensions, quantities, model or part numbers).

    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
    engager
    -0.80
    atteindre
    -0.79
     élèves
    -0.79
    boucles
    -0.78
    Analytic
    -0.77
    esercito
    -0.77
     desaparecer
    -0.75
    vfill
    -0.74
    rétaire
    -0.74
    たとえば
    -0.74
    POSITIVE LOGITS
     Rohit
    0.85
     tun
    0.81
     ceiling
    0.81
     Canopy
    0.81
    天井
    0.81
     Edison
    0.80
     mounting
    0.79
    umm
    0.79
    Ⓘ
    0.78
     Dim
    0.77
    Activations Density 0.011%

    No Known Activations