© 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. 24049
    Prev
    Next
    INDEX
    Explanations

    microscope or microscopy analyzer

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

    The neuron activates for the word "microscope" and related terms like "microscopic" or "microscopy" in scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron responds to occurrences of “micro”-related technical terms (e.g. microscope, microscopy, microsurgery).

    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
    骓
    -2.72
    ——————
    -2.59
     Including
    -2.47
    ————————
    -2.34
    緇
    -2.28
    镦
    -2.25
    放置
    -2.19
    ——–
    -2.19
    leggio
    -2.13
     burch
    -2.13
    POSITIVE LOGITS
    ޏ
    2.39
    ();
    2.28
    .
    2.28
    </h3>
    2.28
    猻
    2.13
    ";
    2.11
    ﮭ
    2.08
    ﱠ
    2.08
    ...
    2.06
    羕
    2.06
    Activations Density 0.021%

    No Known Activations