© 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. 27154
    Prev
    Next
    INDEX
    Explanations

    publication or specification labels

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

    The neuron activates on four-digit year strings (e.g. “2018”, “2017”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    dekat
    -1.77
     and
    -1.48
     jaka
    -1.43
    corrhi
    -1.42
    plastik
    -1.41
    komme
    -1.39
     biela
    -1.38
     podoba
    -1.38
    に入れ
    -1.37
    denk
    -1.37
    POSITIVE LOGITS
    g
    2.17
    u
    2.05
    o
    1.88
    b
    1.74
    ss
    1.73
    i
    1.71
    w
    1.69
    k
    1.68
    e
    1.66
    d
    1.66
    Activations Density 0.000%

    No Known Activations