© 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. 34-GEMMASCOPE-RES-131K
    7. 34656
    Prev
    Next
    INDEX
    Explanations

    biological molecules' functions

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

    scientific/academic text about molecular biology, particularly discussions of proteins, receptors, and gene expression.

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

    The neuron responds to tokens containing digits—i.e. numeric identifiers or numbers embedded in terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     mineures
    -0.91
     traités
    -0.90
    osó
    -0.87
     läm
    -0.84
     Kombin
    -0.84
    gemaakt
    -0.83
     상태
    -0.82
     créées
    -0.82
    inā
    -0.82
    бах
    -0.82
    POSITIVE LOGITS
     involved
    3.17
     involvement
    2.64
     participate
    2.30
     Involved
    2.19
    involved
    2.14
     participation
    1.91
     involve
    1.91
     responsible
    1.86
     play
    1.83
     implicated
    1.82
    Activations Density 0.590%

    No Known Activations