© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66215
    Prev
    Next
    INDEX
    Explanations

    company names and designations

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

    The neuron detects corporate‐legal entity names and designations (e.g. all-caps company names, “Inc.,” “LLC,” “Corporation,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     discussion
    -1.13
     following
    -1.02
     idea
    -0.92
     conversation
    -0.91
     discussed
    -0.88
     اینترن
    -0.85
     discussione
    -0.85
     occasion
    -0.82
    cesis
    -0.81
     arric
    -0.81
    POSITIVE LOGITS
     élevés
    1.04
     normaux
    1.00
     traités
    0.98
     betalen
    0.97
    ooooooo
    0.95
    ímetros
    0.94
     beslu
    0.91
     estimés
    0.91
     mengapa
    0.90
    OGRAPH
    0.90
    Activations Density 0.185%

    No Known Activations