© 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. 10-GEMMASCOPE-RES-131K
    7. 60684
    Prev
    Next
    INDEX
    Explanations

    actin compounds and structures

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

    The neuron detects the term "actin" and its variants in scientific/biological contexts, often related to cellular structures and proteins.

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

    This neuron activates on occurrences of the word “actin.”

    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
    𖣔
    -2.81
    ༛
    -2.81
     elegant
    -2.72
     "
    -2.70
     cinq
    -2.67
     EVEN
    -2.58
    玊
    -2.53
     mange
    -2.52
     trois
    -2.50
    ſſen
    -2.44
    POSITIVE LOGITS
     –
    2.81
    e
    2.53
    se
    2.39
    (
    2.34
     Also
    2.25
    an
    2.22
    ↵↵
    2.19
    s
    2.17
    All
    2.05
    .(
    2.03
    Activations Density 0.002%

    No Known Activations