© 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. 22-GEMMASCOPE-RES-131K
    7. 130385
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on occurrences of the state name “Nebraska” (and its sub‐token fragments).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    Nebraska

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Ꮏ
    -1.77
    𓂂
    -1.75
    ⡦
    -1.72
    ᕱ
    -1.63
    沺
    -1.62
    ständen
    -1.57
    fahrung
    -1.57
     Leurs
    -1.53
    紲
    -1.52
    衚
    -1.51
    POSITIVE LOGITS
    "
    2.19
     ''
    1.80
    which
    1.73
    (
    1.70
     I
    1.50
    vía
    1.49
     week
    1.47
     ‘’
    1.47
     In
    1.42
     Nebraska
    1.42
    Activations Density 0.021%

    No Known Activations