© 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. 22-GEMMASCOPE-RES-131K
    7. 9309
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions

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

    The neuron fires on terms commonly found in formal availability or licensing statements—e.g. “available,” “licensed,” “license,” “MIT,” “under,” and related legal/offer wording.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     such
    -0.98
     pooled
    -0.93
    ঠ
    -0.89
     przede
    -0.88
     Bulan
    -0.88
    sively
    -0.86
     {};
    -0.85
    TokenNameDOT
    -0.84
    mög
    -0.82
    ものである
    -0.82
    POSITIVE LOGITS
    但
    0.94
     with
    0.93
     можно
    0.90
     despues
    0.90
    現在は
    0.88
     nhưng
    0.88
     они
    0.87
    技術
    0.84
     sejak
    0.84
     scopo
    0.84
    Activations Density 0.235%

    No Known Activations