© 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. 616
    Prev
    Next
    INDEX
    Explanations

    tech startups and universities

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

    The neuron strongly responds to mentions of gadgets, inventions, technologies, launch dates, and product-style write-ups—i.e. descriptions of new tech devices or innovations.

    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
    “…”
    -0.75
     آزمون
    -0.74
     olduğu
    -0.74
    Huhu
    -0.74
    ánicos
    -0.74
    sakura
    -0.73
     öde
    -0.73
    ச்
    -0.72
     synergy
    -0.72
     elkaar
    -0.72
    POSITIVE LOGITS
     startup
    1.52
    startup
    1.19
     startups
    1.16
     MIT
    1.06
    Startup
    1.03
    IndexOutOfBounds
    0.96
     universities
    0.96
     researchers
    0.88
    StandardCharsets
    0.87
    unhofer
    0.85
    Activations Density 0.097%

    No Known Activations