© 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. 66637
    Prev
    Next
    INDEX
    Explanations

    clauses following a comma

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

    The neuron activates on words that express intense emotional reactions (especially strong negative emotions like anger or panic).

    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
    傒
    -1.12
     you
    -1.12
     there
    -1.10
    ⎔
    -1.08
    룬
    -1.06
    ческих
    -1.05
     uji
    -1.05
     elektrik
    -1.04
     специально
    -1.03
     bendera
    -1.00
    POSITIVE LOGITS
     but
    1.41
     nevertheless
    1.34
     nonetheless
    1.27
     yet
    1.24
     from
    1.21
     finally
    1.19
     continued
    1.13
     remain
    1.09
     still
    1.08
     dennoch
    1.08
    Activations Density 0.025%

    No Known Activations