© 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. 53950
    Prev
    Next
    INDEX
    Explanations

    film credits, cast, crew

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

    The neuron is looking for four‐digit numbers (years) in the 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
     postwar
    -0.95
     cueva
    -0.77
    Coronavirus
    -0.77
    Instituto
    -0.76
    fir
    -0.75
    Covid
    -0.73
     韓
    -0.73
     deficits
    -0.72
    疫情
    -0.71
     수정
    -0.71
    POSITIVE LOGITS
     Clau
    0.89
     African
    0.74
     Loretta
    0.72
     SE
    0.70
     Stage
    0.69
    クス
    0.68
    gateway
    0.66
     Law
    0.66
     GW
    0.65
    GW
    0.64
    Activations Density 0.046%

    No Known Activations