© 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. 10-GEMMASCOPE-RES-131K
    7. 99425
    Prev
    Next
    INDEX
    Explanations

    time, gifts, promoting, shower

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

    The neuron strongly activates on occurrences of the word “time,” in particular when it marks a temporal reference or duration.

    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
     in
    -2.69
     on
    -2.47
     also
    -2.19
     will
    -2.05
     and
    -1.98
     In
    -1.95
     a
    -1.87
     now
    -1.85
     At
    -1.83
    in
    -1.77
    POSITIVE LOGITS
    ਗ਼
    2.27
     ſte
    2.13
     ſta
    2.11
     repuesto
    2.09
    ⩴
    2.08
    殽
    2.00
    ੴ
    1.99
     konfig
    1.94
     feroit
    1.94
    луйста
    1.92
    Activations Density 0.046%

    No Known Activations