© 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. 67291
    Prev
    Next
    INDEX
    Explanations

    relation between two or more things

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

    The neuron activates on comparative or relational connectors that specify ranges or groupings (e.g. “between,” “both,” “above,” “across”).

    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
     will
    -2.58
     with
    -2.39
     would
    -2.23
     and
    -2.23
     for
    -2.20
     after
    -2.20
     therefore
    -2.13
     one
    -2.08
     also
    -2.02
     so
    -1.94
    POSITIVE LOGITS
    
    1.78
     .........
    1.70
     .......
    1.67
    €“
    1.66
    アクセント
    1.66
     DIDN
    1.63
    ciutto
    1.62
    KommentareTeilen
    1.62
     surtido
    1.61
     ........
    1.59
    Activations Density 0.240%

    No Known Activations