© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75681
    Prev
    Next
    INDEX
    Explanations

    punctuation, new clauses

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

    The neuron strongly activates on blocks of formal/legal boilerplate text—especially copyright, license, and terms-of-use notices.

    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
     since
    -1.13
     it
    -1.08
     informes
    -0.91
     any
    -0.87
     térmico
    -0.82
     bumped
    -0.82
     shrugged
    -0.80
     tecnológico
    -0.80
    pplung
    -0.80
     estrateg
    -0.79
    POSITIVE LOGITS
     них
    0.97
     quelli
    0.94
     которые
    0.93
    Gel
    0.92
     antaranya
    0.86
     them
    0.83
     زوج
    0.83
    ➡
    0.82
     eel
    0.82
     they
    0.82
    Activations Density 0.097%

    No Known Activations