© 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. 39364
    Prev
    Next
    INDEX
    Explanations

    not random, coincidence, isolation

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

    The neuron activates on words that denote randomness or separation (e.g. “random,” “chance,” “isolation”).

    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
     and
    -0.91
     dichter
    -0.90
     doesn
    -0.90
    mam
    -0.84
    zungs
    -0.84
     redak
    -0.82
    而不是
    -0.81
     pero
    -0.81
     استنادى
    -0.81
     anhand
    -0.80
    POSITIVE LOGITS
     there
    1.08
    guitarra
    1.01
     anymore
    0.99
    There
    0.88
    ienen
    0.87
    ihnach
    0.86
     theres
    0.86
    黙
    0.86
    umento
    0.85
     idly
    0.85
    Activations Density 0.031%

    No Known Activations