© 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. 86817
    Prev
    Next
    INDEX
    Explanations

    copyright and license

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

    This neuron activates on boilerplate software license header text (e.g. “You can obtain a copy… under the terms of the 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_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
     Reſ
    -0.98
    anything
    -0.92
    usaha
    -0.88
    kritik
    -0.87
    írito
    -0.87
     novelas
    -0.85
     Tenggara
    -0.85
     museo
    -0.84
    doing
    -0.83
    Ѻ
    -0.82
    POSITIVE LOGITS
     ενώ
    0.86
     prácticamente
    0.83
    cyon
    0.81
     insbesondere
    0.81
     Proceed
    0.80
    belli
    0.79
     soprattutto
    0.78
     spesielt
    0.78
     especially
    0.77
     específicamente
    0.77
    Activations Density 0.113%

    No Known Activations