© 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. 84799
    Prev
    Next
    INDEX
    Explanations

    months and age

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

    The neuron activates on numeric tokens and measurements (e.g. counts, dimensions, dates, and other numbers).

    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
    鏖
    -0.82
    NDICE
    -0.81
     carriera
    -0.79
     зару
    -0.79
    سان
    -0.79
    зать
    -0.78
    zedł
    -0.77
     diny
    -0.77
    ั่น
    -0.74
    missao
    -0.74
    POSITIVE LOGITS
     anywhere
    0.90
    一二
    0.89
     porción
    0.88
    *-
    0.86
    ()-
    0.82
    东西
    0.79
    ?-
    0.78
     everywhere
    0.77
     }}-
    0.76
    anywhere
    0.75
    Activations Density 0.115%

    No Known Activations