© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 4073
    Prev
    Next
    INDEX
    Explanations

    Cebu, Kansas, Amnesty, Q:

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

    This neuron detects uppercase or title‐case tokens corresponding to named entities or proper nouns (e.g. organization names, locations, persons).

    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
     Westchester
    -0.97
     Hanoi
    -0.86
     Delhi
    -0.81
     Kurdish
    -0.80
    leden
    -0.80
     pasas
    -0.79
     Caracas
    -0.79
     Hertfordshire
    -0.79
     Piedmont
    -0.78
     Sonoma
    -0.77
    POSITIVE LOGITS
     Cebu
    1.70
     Cebuano
    1.33
    Kansas
    0.87
     Cheltenham
    0.85
     nga
    0.81
     Gloucester
    0.79
     Malvern
    0.78
     Kansas
    0.76
     Bevan
    0.73
    筋
    0.72
    Activations Density 0.010%

    No Known Activations