© 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. 10-GEMMASCOPE-RES-131K
    7. 13284
    Prev
    Next
    INDEX
    Explanations

    how long things last

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

    This neuron responds to mentions of length or duration—e.g. words and numbers indicating how long something lasts or lives.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     hunne
    -1.65
     Exacts
    -1.34
    ⢊
    -1.32
     jedis
    -1.30
     geburtstag
    -1.30
    ÑOS
    -1.30
    .」
    -1.30
     kleines
    -1.28
    aimeJ
    -1.28
     wart
    -1.27
    POSITIVE LOGITS
     on
    1.55
     by
    1.43
     in
    1.20
     like
    1.20
     d
    1.18
     to
    1.16
     vaše
    1.13
     In
    1.11
     ибо
    1.10
    such
    1.09
    Activations Density 0.073%

    No Known Activations