© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6234
    Prev
    Next
    INDEX
    Explanations

    immobility or confinement

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

    The neuron activates on words and forms that describe being confined, trapped, imprisoned, stuck, or locked.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ಯ್
    0.56
    봤
    0.56
     sparsely
    0.55
    勺
    0.54
    削
    0.53
    撿
    0.53
     trustworthiness
    0.53
    ceğiz
    0.52
     weaknesses
    0.52
    솜
    0.52
    POSITIVE LOGITS
     trapped
    1.91
     locked
    1.84
    locked
    1.80
     stuck
    1.73
    Locked
    1.72
     Locked
    1.69
     lock
    1.57
     LOCKED
    1.54
     locking
    1.48
     আটকে
    1.46
    Activations Density 0.527%

    No Known Activations