© 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. 22-GEMMASCOPE-RES-131K
    7. 10832
    Prev
    Next
    INDEX
    Explanations

    therapeutic and stimulating activities

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

    The neuron strongly fires on mentions of specific tools, products, or branded names (e.g. “text magnifier,” “Beeminder,” “Seaside Sensory Scene”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ,
    -1.17
     Epif
    -1.12
     brillant
    -1.11
     beaute
    -1.10
    显得
    -1.07
     précédents
    -1.04
    ַּ
    -1.02
     amour
    -1.02
    шого
    -1.00
     groei
    -1.00
    POSITIVE LOGITS
     helps
    1.61
     triggers
    1.46
     help
    1.45
     cukru
    1.35
     helping
    1.33
     helped
    1.32
    ἵ
    1.27
    ׇ
    1.25
     Američ
    1.24
     stimuli
    1.23
    Activations Density 0.053%

    No Known Activations