© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 44973
    Prev
    Next
    INDEX
    Explanations

    finger protein, ZIP protein

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

    scientific or technical terms that include specific molecular structures, chemicals, or programming components.

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

    The neuron responds to individual domain-specific technical or scientific terms (e.g. class names, chemical or biological molecule names, specialized jargon).

    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
     and
    -1.82
    Some
    -1.71
     Перейти
    -1.58
     Kriege
    -1.56
    所有的
    -1.55
     one
    -1.54
    ႐
    -1.51
    What
    -1.50
    There
    -1.49
     The
    -1.48
    POSITIVE LOGITS
    esercito
    1.34
    隂
    1.30
     patrimoine
    1.30
     francès
    1.24
     estekak
    1.23
     intens
    1.23
     promesse
    1.23
    歘
    1.23
    𝐂
    1.23
    わけです
    1.21
    Activations Density 0.119%

    No Known Activations