© 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. 10-GEMMASCOPE-RES-131K
    4. 42607
    Prev
    Next
    INDEX
    Explanations

    get them to

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

    This neuron activates on expressions of influencing or causing someone to do something—i.e. verbs or phrases of persuasion followed by an action (“get you to…,” “make Joe fall…,” “influencing voters,” etc.).

    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
     такого
    -1.34
    such
    -1.33
     таких
    -1.30
     such
    -1.27
     такой
    -1.23
    гают
    -1.20
     такую
    -1.20
    INUM
    -1.17
     muitos
    -1.16
    already
    -1.12
    POSITIVE LOGITS
     about
    1.95
     by
    1.64
     for
    1.51
     into
    1.46
     through
    1.37
    lossenen
    1.28
     relevant
    1.27
     important
    1.21
    dreamstime
    1.16
     which
    1.16
    Activations Density 0.057%

    No Known Activations