© 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. 60560
    Prev
    Next
    INDEX
    Explanations

    when action is needed

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

    The neuron strongly activates on common short function words—especially pronouns and auxiliaries like “it,” “was,” “when,” and similar tokens.

    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
     olyan
    -0.88
    EXIST
    -0.85
     florales
    -0.84
     می‌گوید
    -0.84
    assumed
    -0.83
     Наде
    -0.83
    igné
    -0.80
    şiv
    -0.79
    解决了
    -0.79
     udało
    -0.79
    POSITIVE LOGITS
     indicated
    3.05
     warranted
    3.02
     appropriate
    2.77
     justified
    2.20
     indicado
    1.98
    indicated
    1.93
    appropriate
    1.91
     needed
    1.85
     Indic
    1.84
     advisable
    1.83
    Activations Density 0.090%

    No Known Activations