© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67891
    Prev
    Next
    INDEX
    Explanations

    contact or opposition

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

    The neuron strongly activates on the preposition “against,” i.e. when one thing is described as coming into contact with or colliding against another.

    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
    .
    -2.70
    </h2>
    -2.02
     Alternatively
    -1.63
    _
    -1.59
     universitaria
    -1.54
     Yesterday
    -1.52
     sofrer
    -1.52
    In
    -1.48
     Before
    -1.42
     Throughout
    -1.42
    POSITIVE LOGITS
    YNAMICS
    1.73
    
    1.67
     <<<<<<<<<<<<<<
    1.66
     esposo
    1.66
    NEYS
    1.66
     ausein
    1.65
    StoryboardSegue
    1.64
    ౭
    1.62
     machten
    1.61
    </u>
    1.59
    Activations Density 0.012%

    No Known Activations