© 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. 59016
    Prev
    Next
    INDEX
    Explanations

    readiness or anticipation

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

    The neuron activates on expressions of imminent occurrence or readiness—phrases like “poised to,” “primed for,” etc., signaling that something is about to happen.

    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
    :
    -2.86
    ve
    -2.38
    a
    -2.11
    ”-
    -2.06
    敺
    -2.05
    ”;
    -2.03
    1
    -2.03
    麃
    -2.02
     ”
    -2.00
    -”
    -2.00
    POSITIVE LOGITS
    '
    2.66
     faune
    2.19
    transQ
    2.16
    了你
    2.02
    ⑊
    1.98
    งิน
    1.95
    が行
    1.93
    钇
    1.92
     fuite
    1.91
     券
    1.90
    Activations Density 0.002%

    No Known Activations