© 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. 38767
    Prev
    Next
    INDEX
    Explanations

    handcuffs and being tied

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

    The main thing this neuron does is find mentions of physical restraints or bindings (e.g., handcuffs, chains, cuffs, restraints).

    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
    ってしまう
    -1.59
    de
    -1.45
    Keto
    -1.41
     telle
    -1.34
    .
    -1.33
    Kubernetes
    -1.32
    all
    -1.31
    í
    -1.31
    le
    -1.30
    firm
    -1.29
    POSITIVE LOGITS
     misalnya
    1.72
     diberikan
    1.70
     Eigentü
    1.65
     diikuti
    1.63
    ční
    1.61
     Different
    1.59
    consin
    1.59
     Füßen
    1.57
    媖
    1.56
     Unterschied
    1.53
    Activations Density 0.019%

    No Known Activations