© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82978
    Prev
    Next
    INDEX
    Explanations

    proper nouns and locations

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

    The neuron is primarily detecting year‐style numbers (dates) in text.

    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
    ckeye
    -0.78
    ậc
    -0.77
     marginal
    -0.75
    غات
    -0.73
     microscopic
    -0.72
    niczka
    -0.70
     accidental
    -0.70
    テラス
    -0.69
    Cuándo
    -0.69
    ときの
    -0.68
    POSITIVE LOGITS
     Lithuania
    0.88
     Vilnius
    0.85
     cutters
    0.77
    gegeven
    0.77
    Gift
    0.77
     Polskiej
    0.74
     boilers
    0.73
    gados
    0.71
     Lithuanian
    0.71
     trellis
    0.71
    Activations Density 0.004%

    No Known Activations