© 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. 34-GEMMASCOPE-RES-131K
    7. 66016
    Prev
    Next
    INDEX
    Explanations

    kraft pulp

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

    The neuron fires on specialized dental/restorative terminology—especially phrases naming tooth structures (e.g. dentinal, pulpal), procedures (e.g. restorations, resin composites), and associated fluid‐movement or sensitivity phenomena in teeth.

    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
    ∥
    -0.71
     пиро
    -0.70
    petit
    -0.66
     Reifen
    -0.66
    orbit
    -0.65
     Typen
    -0.65
    ishments
    -0.65
    wicket
    -0.63
    crs
    -0.63
     Пав
    -0.63
    POSITIVE LOGITS
     pulp
    2.64
     Pulp
    2.20
    Pulp
    1.97
     pul
    1.95
     PUL
    1.44
     Pul
    1.42
    pul
    1.36
     pulpit
    1.28
    PUL
    1.24
     пуль
    1.22
    Activations Density 0.097%

    No Known Activations