© 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. 38895
    Prev
    Next
    INDEX
    Explanations

    specific actions or states

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

    The neuron responds to words and phrases describing falling asleep, being asleep, or waking up.

    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
     vriende
    -1.51
     konflikt
    -1.45
     kontrak
    -1.34
     Sitten
    -1.34
     geweldige
    -1.30
     respek
    -1.30
     parku
    -1.28
     eenig
    -1.27
    ↵↵
    -1.26
     GLOBAL
    -1.26
    POSITIVE LOGITS
     several
    1.54
     two
    1.40
    With
    1.38
     three
    1.37
     mainly
    1.33
     very
    1.30
     use
    1.30
     when
    1.29
     while
    1.29
     our
    1.27
    Activations Density 0.085%

    No Known Activations