© 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. 113013
    Prev
    Next
    INDEX
    Explanations

    MIT license text

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

    references to the MIT License in code files and documentation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron detects mentions of software licenses (e.g., “MIT License,” “Apache License”).

    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
    rvats
    -1.62
    ResumeLayout
    -1.53
     and
    -1.52
     then
    -1.49
    Revenir
    -1.45
    紲
    -1.43
     of
    -1.41
    ется
    -1.39
    rugu
    -1.38
    ྅
    -1.37
    POSITIVE LOGITS
     spécifique
    2.06
    "
    1.91
     légale
    1.84
    ????
    1.83
    3
    1.80
    蕻
    1.80
     suéter
    1.75
     préféré
    1.72
     MANY
    1.70
     MUCH
    1.70
    Activations Density 0.008%

    No Known Activations