© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103700
    Prev
    Next
    INDEX
    Explanations

    accuracy | acc db | acc parallel

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

    The neuron responds to any token containing the substring “acc.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     It
    -3.05
     Here
    -2.58
     If
    -2.52
     ähnlichen
    -2.48
     To
    -2.44
        
    -2.42
            
    -2.39
    سجيلات
    -2.39
     But
    -2.39
      
    -2.36
    POSITIVE LOGITS
    柃
    3.14
    t
    2.83
    ῞
    2.69
    鰱
    2.58
    up
    2.58
    k
    2.53
    Mereka
    2.50
    after
    2.50
    鳢
    2.50
    Karakteristik
    2.47
    Activations Density 0.007%

    No Known Activations