© 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. 22133
    Prev
    Next
    INDEX
    Explanations

    resting state and measurements

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

    The neuron consistently activates on occurrences of the adjective “resting” (e.g. resting membrane potential, resting discharge activity, resting state).

    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
     zoude
    -3.44
     krim
    -3.25
     vitale
    -3.08
    Ꮠ
    -3.06
    桖
    -3.05
     kredi
    -3.00
     distrik
    -2.98
     ܙ
    -2.95
     célè
    -2.94
     dezelve
    -2.94
    POSITIVE LOGITS
     With
    3.03
    -
    2.91
     That
    2.77
     To
    2.69
    -"
    2.45
     )
    2.45
    …
    2.45
     What
    2.44
     Using
    2.42
     Not
    2.41
    Activations Density 0.004%

    No Known Activations