© 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. 67975
    Prev
    Next
    INDEX
    Explanations

    plasminogen activator / imatinib mesylate

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

    scientific or technical terms in biochemistry and molecular biology.

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

    The neuron principally detects biochemical compound names and related molecular terms (e.g. enzyme or chemical compound tokens).

    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
     also
    -1.77
     even
    -1.65
     there
    -1.55
     incluso
    -1.55
     antara
    -1.46
     their
    -1.44
     between
    -1.40
     any
    -1.36
     its
    -1.33
     "
    -1.27
    POSITIVE LOGITS
    Carcinogenicity
    1.44
     problemen
    1.38
     resultaten
    1.30
     سينما
    1.29
     veranderen
    1.28
     muur
    1.27
     zijne
    1.23
     bescha
    1.23
     gewicht
    1.23
     lijst
    1.23
    Activations Density 0.429%

    No Known Activations