© 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. 48858
    Prev
    Next
    INDEX
    Explanations

    Lehigh Valley names

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

    This neuron strongly fires on tokens containing the letter sequence “igh,” as in Lehigh, Leigh, Binghamton (–ingham–), Conemaugh (–emaugh–), etc.

    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
    ‚¬
    -0.75
    ⁡
    -0.74
    Argument
    -0.73
    bold
    -0.71
     Schleswig
    -0.70
     Cranston
    -0.70
     בני
    -0.69
     ideale
    -0.68
    ographie
    -0.67
    endal
    -0.67
    POSITIVE LOGITS
    陉
    0.77
     Valley
    0.73
    之助
    0.72
     Fren
    0.70
     Hanson
    0.68
    TON
    0.67
     Pears
    0.66
    beti
    0.66
    isak
    0.64
    Creator
    0.63
    Activations Density 0.038%

    No Known Activations