© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66084
    Prev
    Next
    INDEX
    Explanations

    past actions over periods of time

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

    The neuron flags numeric expressions—tokens representing quantities, counts, or digits.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     after
    -2.39
     currently
    -2.23
     recently
    -2.20
     today
    -2.19
     now
    -2.16
     when
    -2.09
     before
    -2.06
     yesterday
    -2.02
     last
    -1.91
     during
    -1.85
    POSITIVE LOGITS
    basically
    1.23
    uded
    1.23
    various
    1.23
    越来越
    1.22
    鶿
    1.19
    mostly
    1.18
     både
    1.17
    several
    1.16
     ofte
    1.16
    lllll
    1.16
    Activations Density 0.103%

    No Known Activations