© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64371
    Prev
    Next
    INDEX
    Explanations

    time intervals and durations

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

    The neuron fires on numeric tokens (i.e. any standalone numbers) in the text.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     on
    -1.14
    ּוֹ
    -1.06
    Rptr
    -1.00
    ᾽
    -0.96
     from
    -0.96
     information
    -0.95
     which
    -0.93
    וּ
    -0.93
    Rö
    -0.93
    queryInterface
    -0.91
    POSITIVE LOGITS
     لمدة
    1.13
    ▎
    1.07
    ಠ
    1.02
    bihi
    1.01
     empreg
    0.99
     PUSH
    0.97
    ayy
    0.96
    duration
    0.96
     duration
    0.96
     estekak
    0.95
    Activations Density 0.003%

    No Known Activations