© 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. 15051
    Prev
    Next
    INDEX
    Explanations

    awaiting or waiting for something

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

    The neuron activates on words signaling a pending or waiting state (e.g. “awaiting,” “waiting”).

    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
    s
    -1.59
    ty
    -1.45
    1
    -1.44
    même
    -1.43
     utilizada
    -1.29
     сына
    -1.28
    even
    -1.28
     acoged
    -1.27
     ومن
    -1.23
     always
    -1.21
    POSITIVE LOGITS
     to
    1.92
     someone
    1.91
     the
    1.77
     a
    1.75
    禵
    1.36
    isait
    1.34
    骓
    1.26
     it
    1.23
    }%
    1.20
     entweder
    1.20
    Activations Density 0.015%

    No Known Activations