© 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. 10-GEMMASCOPE-RES-131K
    7. 112151
    Prev
    Next
    INDEX
    Explanations

    none or if any

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

    The neuron fires on words that express absence or open-ended quantity—e.g. “none,” “anything,” or similar indefinite/zero-amount terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    SOME
    -1.41
     februari
    -1.30
    🧐
    -1.30
    喈
    -1.29
     Bioaccumulative
    -1.27
    糴
    -1.25
    karten
    -1.23
     NATIONAL
    -1.22
    IMENT
    -1.22
    涐
    -1.21
    POSITIVE LOGITS
     other
    1.59
     None
    1.40
     more
    1.36
     либо
    1.34
     Both
    1.34
     varied
    1.29
     increased
    1.27
     Many
    1.27
    <h3>
    1.26
     it
    1.25
    Activations Density 0.108%

    No Known Activations