© 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. 22-GEMMASCOPE-RES-131K
    7. 27419
    Prev
    Next
    INDEX
    Explanations

    numbers and times

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

    This neuron responds to numeric tokens that denote dates and times (e.g. calendar dates and clock times).

    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
     Bewegungen
    -1.21
     escritório
    -1.17
    Jörg
    -1.16
     Verhältnisse
    -1.16
     comentários
    -1.14
    橚
    -1.13
     entré
    -1.10
     Absicht
    -1.10
     Auffassung
    -1.09
    日記
    -1.07
    POSITIVE LOGITS
     or
    1.41
    </h2>
    1.19
     and
    1.13
     by
    1.03
    </b>
    1.02
    不
    1.01
     from
    1.01
     மற்ற
    0.99
     declining
    0.99
    üyada
    0.99
    Activations Density 0.003%

    No Known Activations