© 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. 71836
    Prev
    Next
    INDEX
    Explanations

    cells and anatomy

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

    numeric values within text, especially in scientific or technical contexts.

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

    This neuron responds to terms common in biomedical and life‐science research descriptions (e.g., cell types, physiological processes, experimental conditions).

    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
     terciopelo
    -1.27
     eenen
    -1.03
    今天
    -1.01
     conftest
    -1.01
    Δείτε
    -0.99
     tehd
    -0.98
     meravigli
    -0.97
     leopardo
    -0.96
     fordert
    -0.95
     vám
    -0.95
    POSITIVE LOGITS
     in
    1.15
     on
    1.05
     with
    0.92
    no
    0.84
    et
    0.81
     pretend
    0.79
    uksi
    0.79
     using
    0.78
     plating
    0.77
    िये
    0.77
    Activations Density 0.071%

    No Known Activations