© 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. 65177
    Prev
    Next
    INDEX
    Explanations

    instructions and reflections about time

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

    The neuron strongly activates on direct calls to action and motivational, future-oriented phrasing (imperatives and “you will…” style language).

    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
     visse
    -1.20
     vru
    -1.20
    һы
    -1.14
     sentiers
    -1.10
     épaules
    -1.09
    ℮
    -1.09
     FIFTH
    -1.09
    ocirc
    -1.06
    mitten
    -1.06
     étages
    -1.05
    POSITIVE LOGITS
     your
    2.17
     you
    1.80
     yourself
    1.66
     today
    1.62
     start
    1.51
     beginning
    1.45
     begin
    1.41
     this
    1.35
     now
    1.30
     one
    1.25
    Activations Density 0.018%

    No Known Activations