© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67825
    Prev
    Next
    INDEX
    Explanations

    Perry and waterfront locations

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

    The neuron fires on single-word, capitalized geographic names (e.g. Perry, Waterfront, Dahme).

    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
    our
    -3.16
    le
    -2.95
    if
    -2.73
    it
    -2.72
    and
    -2.59
    ization
    -2.53
    焢
    -2.50
    v
    -2.42
    as
    -2.33
    驟
    -2.30
    POSITIVE LOGITS
    寕
    2.80
    禤
    2.73
    
    2.66
    ╿
    2.64
    荩
    2.59
     prende
    2.52
     lidé
    2.48
     It
    2.48
    تیجه
    2.44
    罴
    2.44
    Activations Density 0.010%

    No Known Activations