© 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. 11979
    Prev
    Next
    INDEX
    Explanations

    inability to act or function

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

    This neuron fires on words and tokens that express an inability or incapacity (e.g. can’t, couldn’t, unable, not able).

    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
    organe
    -0.89
     CHANGES
    -0.75
     Editorial
    -0.75
    dė
    -0.75
     OPTIONS
    -0.75
    तर
    -0.75
    原地
    -0.74
    Comments
    -0.74
     [-
    -0.73
     verbind
    -0.73
    POSITIVE LOGITS
     function
    1.80
     even
    1.59
     functioning
    1.53
    function
    1.53
     focus
    1.51
     concentrate
    1.48
     Function
    1.38
     concentrating
    1.36
     sleep
    1.30
     functions
    1.30
    Activations Density 0.033%

    No Known Activations