© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54055
    Prev
    Next
    INDEX
    Explanations

    options or choices

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

    The neuron fires strongly on content words that are part of enumerated feature or option lists—i.e. the key items in a bulleted or comma-separated list of offerings.

    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
    ReadWrite
    -0.82
    uffff
    -0.81
     hochwertige
    -0.80
     insuper
    -0.79
     comunicarse
    -0.79
    ellum
    -0.78
     sustituir
    -0.78
    PUBLISH
    -0.77
    췄
    -0.77
     devised
    -0.76
    POSITIVE LOGITS
     cepat
    1.00
     opt
    0.95
    tament
    0.95
     resultado
    0.94
     peux
    0.94
     batalla
    0.93
     enemmän
    0.92
     предпочита
    0.88
     lieber
    0.86
    المراجع
    0.85
    Activations Density 0.058%

    No Known Activations