© 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. 82537
    Prev
    Next
    INDEX
    Explanations

    OR CONDITIONS

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

    The neuron strongly activates on all-caps words (particularly in license boilerplate), e.g. "WITHOUT", "WARRANTIES", and "OR".

    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
     deployment
    -0.76
     Deployment
    -0.76
    bibitem
    -0.73
     suicides
    -0.71
    deployment
    -0.71
    GREATER
    -0.69
    Deployment
    -0.69
     Calvary
    -0.69
    álním
    -0.68
    valueOf
    -0.68
    POSITIVE LOGITS
     gil
    0.78
     SANG
    0.77
     below
    0.72
     ogn
    0.72
     USES
    0.71
     VERS
    0.68
     tausend
    0.68
     Rè
    0.65
     hints
    0.65
     proveniente
    0.64
    Activations Density 0.088%

    No Known Activations