© 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. 34-GEMMASCOPE-RES-131K
    7. 48903
    Prev
    Next
    INDEX
    Explanations

    unicode, unimodules, uniprot

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

    This neuron activates on tokens containing the substring “uni” (e.g. Unicode, UniProt, unidecode, unimodules, unimap, etc.).

    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
    सु
    -0.75
    verse
    -0.73
     карто
    -0.73
     coalition
    -0.71
     Five
    -0.71
     Conditional
    -0.70
    Stokes
    -0.70
     Mixed
    -0.70
     resign
    -0.69
     Kirche
    -0.68
    POSITIVE LOGITS
     zina
    0.82
     Unic
    0.81
     umo
    0.79
     lorsqu
    0.75
    ði
    0.75
    🦄
    0.73
     firebaseConfig
    0.73
     tena
    0.71
    肼
    0.71
     gestaltet
    0.71
    Activations Density 0.028%

    No Known Activations