© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79488
    Prev
    Next
    INDEX
    Explanations

    New Hampshire

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

    The neuron strongly activates on mentions of New Hampshire place names and related jurisdictional terms (e.g. counties, towns, facilities).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     constantly
    -0.73
    ァ
    -0.72
    طر
    -0.71
     miał
    -0.69
    foundland
    -0.68
     médaille
    -0.66
     kepad
    -0.66
    هور
    -0.65
    CARD
    -0.65
    MeasureSpec
    -0.65
    POSITIVE LOGITS
     NH
    1.97
    NH
    1.60
     Portsmouth
    1.53
     Nash
    1.28
     nh
    1.27
     Manchester
    1.24
     Nh
    1.24
    nh
    1.23
     Granite
    1.18
    Granite
    1.17
    Activations Density 0.043%

    No Known Activations