© 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. 34-GEMMASCOPE-RES-131K
    7. 117597
    Prev
    Next
    INDEX
    Explanations

    license agreement terms

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

    The neuron detects bits of legal‐license text—particularly “terms of the … license” and related section or version references.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     according
    -2.61
    According
    -1.91
    according
    -1.70
     According
    -1.69
     podľa
    -1.58
     selon
    -1.33
    根据
    -1.32
     ACCORD
    -1.27
     secondo
    -1.27
     según
    -1.26
    POSITIVE LOGITS
    るか
    0.93
     dictates
    0.82
     prescriptions
    0.81
     specifications
    0.81
     norms
    0.79
     vigente
    0.78
    
    0.77
    ⋄
    0.77
     Wortes
    0.76
     but
    0.75
    Activations Density 0.083%

    No Known Activations