© 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. 27235
    Prev
    Next
    INDEX
    Explanations

    biological: organisms, cells, tissues

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

    terms and concepts related to biological organisms, processes, and systems.

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

    The neuron activates on terms referring to biological or biochemical entities and processes.

    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
    4
    -1.00
    PropertyChanged
    -0.97
     lápis
    -0.94
    着一个
    -0.93
    ramientas
    -0.93
    ERSHIP
    -0.92
    0
    -0.90
     you
    -0.89
    SetItem
    -0.88
    rophilic
    -0.88
    POSITIVE LOGITS
     biological
    1.27
    Biological
    1.12
     Biological
    1.00
    feel
    0.94
    human
    0.93
     biologic
    0.93
    stufen
    0.92
    Humans
    0.91
     organismes
    0.91
    darah
    0.91
    Activations Density 0.202%

    No Known Activations