© 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. 13594
    Prev
    Next
    INDEX
    Explanations

    logical and feasibility checks

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

    The neuron fires on phrases expressing that something “makes sense” (or doesn’t), i.e. statements about logical coherence.

    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
    艷
    0.55
    힝
    0.55
    भाग्य
    0.54
    閭
    0.54
    ఎస్
    0.53
    Спољашње
    0.53
     lệ
    0.53
    擷
    0.53
    জীবন
    0.52
    HERSHEY
    0.52
    POSITIVE LOGITS
     sense
    2.30
     Sense
    2.00
    sense
    1.95
     sentido
    1.93
    Sense
    1.88
     logic
    1.87
     logical
    1.84
    逻辑
    1.81
     lógica
    1.76
     Logical
    1.73
    Activations Density 0.155%

    No Known Activations