© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64358
    Prev
    Next
    INDEX
    Explanations

    actions and requirements

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

    The neuron is triggered by formal technical or legal‐style language—especially requirement/modality words and phrases typical of patent specifications (e.g. “to,” “must,” “required,” “provided,” etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     there
    -1.83
     some
    -1.54
     it
    -1.53
     they
    -1.40
     no
    -1.38
    (!_
    -1.35
     not
    -1.34
     sadly
    -1.27
     nothing
    -1.25
     only
    -1.24
    POSITIVE LOGITS
    度
    1.58
     poë
    1.55
     Projektu
    1.46
    consejos
    1.45
    
    1.44
     comenzará
    1.43
     volverá
    1.43
    力
    1.42
    Believe
    1.40
     OGSÅ
    1.37
    Activations Density 0.053%

    No Known Activations