© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 11938
    Prev
    Next
    INDEX
    Explanations

    mediated biological processes

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

    biological research terms related to cellular processes and disease mechanisms.

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

    The neuron strongly activates on technical molecular‐biology terms describing protein or gene activity (e.g. “translocation,” “expression,” “activation,” “inhibits,” pathways, cell types).

    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
     for
    -1.60
     with
    -1.48
     from
    -1.13
    使用
    -1.08
     softwares
    -1.05
     using
    -0.98
     برای
    -0.97
     menggunakan
    -0.94
     ovviamente
    -0.93
    สำหรับ
    -0.93
    POSITIVE LOGITS
     via
    2.34
     through
    1.88
     but
    1.85
     путем
    1.61
    via
    1.58
     by
    1.50
     poprzez
    1.47
    presumably
    1.46
     even
    1.45
     in
    1.43
    Activations Density 0.611%

    No Known Activations