© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12762
    Prev
    Next
    INDEX
    Explanations

    ready for or expecting something

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

    The neuron flags imperative “get ready”/“prepare to” style calls to action (e.g. “Prepare to…,” “Get ready for…,” “Get ready to…”)

    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
     would
    -1.48
     so
    -1.48
     its
    -1.45
     allows
    -1.16
    uş
    -1.13
     evitando
    -1.09
     what
    -1.09
    单独
    -1.05
     kedu
    -1.02
     Why
    -1.00
    POSITIVE LOGITS
    possibly
    1.24
     yourself
    1.21
     insanların
    1.15
     hlavy
    1.15
     yourselves
    1.14
    potentially
    1.13
     também
    1.12
    likely
    1.11
     גם
    1.05
     your
    1.02
    Activations Density 0.023%

    No Known Activations