© 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. 34-GEMMASCOPE-RES-131K
    7. 49005
    Prev
    Next
    INDEX
    Explanations

    place names and specific terms

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

    This neuron fires on tokens in passages containing numeric or quantifiable details (dates, figures, counts, amounts).

    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
     Thames
    -1.06
     Medford
    -1.05
     Karnataka
    -1.00
     Sussex
    -1.00
     Dorset
    -0.96
     Canterbury
    -0.89
     Londres
    -0.89
     Hampstead
    -0.89
     London
    -0.88
    Brighton
    -0.88
    POSITIVE LOGITS
     Lancashire
    1.21
     Youngstown
    1.02
     Blackpool
    1.00
     Nant
    0.91
    cashire
    0.90
     Wigan
    0.88
     lads
    0.88
     constituted
    0.84
     Huddersfield
    0.84
     Anfield
    0.83
    Activations Density 0.065%

    No Known Activations