© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39118
    Prev
    Next
    INDEX
    Explanations

    inverter unit

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

    The neuron fires strongly on technical machinery terms—especially names of mechanical or electrical devices (e.g. “pump,” “inverter,” “converter”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    忸
    -1.48
     vermelhas
    -1.47
     Gruß
    -1.44
    ?”
    -1.41
     Forderungen
    -1.41
     notwendigen
    -1.40
     Wurzeln
    -1.34
    锲
    -1.34
    涇
    -1.34
    私たちは
    -1.31
    POSITIVE LOGITS
     conmigo
    1.67
    e
    1.63
     saa
    1.44
    WEAPON
    1.31
     déput
    1.30
    ции
    1.30
    onatos
    1.27
     女人
    1.24
     araw
    1.23
    na
    1.22
    Activations Density 0.029%

    No Known Activations