© 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. 10-GEMMASCOPE-RES-131K
    7. 43032
    Prev
    Next
    INDEX
    Explanations

    beer, brewing, and ingredients

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

    beer and brewery-related terminology, including beer styles, brewing processes, and company names.

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

    The neuron fires on mentions of brewery or brewing‐company names and related 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_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
     during
    -1.63
    mathrm
    -1.43
    sữa
    -1.41
     that
    -1.34
     after
    -1.34
     léka
    -1.32
     high
    -1.29
     pervasive
    -1.26
     specified
    -1.24
     maneu
    -1.22
    POSITIVE LOGITS
     eki
    1.39
     eorum
    1.38
     instalación
    1.38
     omnes
    1.34
     molti
    1.28
     raha
    1.28
     nini
    1.27
     shirts
    1.23
     kamb
    1.22
     kuni
    1.20
    Activations Density 0.061%

    No Known Activations