© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9131
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric and time‐related expressions (like “seven weeks,” “7-minute,” “every time,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0.84
     因为
    0.82
     which
    0.81
     които
    0.80
    因为
    0.78
     of
    0.77
     因為
    0.73
    以及
    0.71
    5
    0.71
    2
    0.71
    POSITIVE LOGITS
     pertinente
    0.85
     preferências
    0.83
     notícias
    0.82
     relevante
    0.79
     divertido
    0.79
     teamwork
    0.78
     восприя
    0.78
    publishing
    0.78
     смысл
    0.78
     coercion
    0.77
    Activations Density 0.000%

    No Known Activations