© 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. 84330
    Prev
    Next
    INDEX
    Explanations

    blocking, sealing, or closing off

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

    This neuron detects words referring to openings or barriers (doors, windows, glass) often in the context of something moving through or pressing against them.

    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
     않는
    -0.93
    ياب
    -0.85
    стого
    -0.82
     βα
    -0.81
     freno
    -0.81
     zones
    -0.77
    arques
    -0.76
    リヤ
    -0.76
     evaporation
    -0.76
    uação
    -0.76
    POSITIVE LOGITS
     locked
    1.17
     sealed
    1.16
    locked
    1.02
    隔
    1.02
    Locked
    0.98
     blocked
    0.97
     Locked
    0.94
     closed
    0.91
     partition
    0.90
     attraverso
    0.89
    Activations Density 0.077%

    No Known Activations