© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83129
    Prev
    Next
    INDEX
    Explanations

    company industry information

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

    The neuron fires strongly on the words “Industry” or “Industrial” (and related compounds) when they appear as part of organization names or sector labels.

    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
     rire
    -0.84
    ఎ
    -0.78
    āju
    -0.78
    אל
    -0.78
     jugement
    -0.77
    Ⓚ
    -0.76
     yder
    -0.75
    Dès
    -0.75
     clubes
    -0.75
    artament
    -0.75
    POSITIVE LOGITS
    NEG
    0.82
     deaktiviert
    0.82
    mu
    0.78
     vao
    0.77
    naught
    0.75
     cornu
    0.75
    ⪢
    0.75
    ุต
    0.75
    ⟭
    0.74
     enquanto
    0.73
    Activations Density 0.023%

    No Known Activations