© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116345
    Prev
    Next
    INDEX
    Explanations

    toy licensing

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

    This neuron activates on words that are part of named titles or proper‐name headings (e.g. section titles, product names, event names, and award names).

    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
    requireNonNull
    -0.87
    iget
    -0.77
     wastes
    -0.77
    购
    -0.76
    brero
    -0.75
    宰
    -0.75
    malink
    -0.75
    rices
    -0.74
    ))-
    -0.74
    éndolo
    -0.73
    POSITIVE LOGITS
     toy
    1.47
     licensing
    1.41
    Licensing
    1.30
     licensees
    1.27
     Licensing
    1.26
     licensee
    1.17
     лицен
    1.14
     licenses
    1.09
    toy
    1.08
     toys
    1.07
    Activations Density 0.018%

    No Known Activations