© 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. 10-GEMMASCOPE-RES-131K
    7. 69100
    Prev
    Next
    INDEX
    Explanations

    medical and professional terms

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

    This neuron detects specific nouns and proper names across various contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     также
    -1.45
     also
    -1.41
    Инг
    -1.37
     також
    -1.35
     também
    -1.34
     piłkarz
    -1.33
     también
    -1.31
    蟜
    -1.30
     olmak
    -1.29
     myös
    -1.28
    POSITIVE LOGITS
     already
    1.37
    ()">
    1.33
     bestimmte
    1.30
    quarelle
    1.25
     like
    1.23
     bestimmten
    1.21
     bestimm
    1.20
     with
    1.19
    {?>
    1.19
     from
    1.16
    Activations Density 0.723%

    No Known Activations