© 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. 36079
    Prev
    Next
    INDEX
    Explanations

    code examples and tests

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

    The neuron fires on numeric literals (tokens composed of digits, including integers and decimals).

    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
    がありますが
    -1.00
     tages
    -1.00
     other
    -0.97
     knap
    -0.97
     REMOVE
    -0.97
     NOO
    -0.94
    teness
    -0.92
    genous
    -0.92
     завжди
    -0.92
     Superhosts
    -0.91
    POSITIVE LOGITS
     Example
    1.41
     example
    1.38
    Example
    1.21
     bijvoorbeeld
    1.11
     examples
    1.11
     given
    1.08
     với
    1.08
     esimerkiksi
    1.03
     gewohnt
    1.02
     with
    1.00
    Activations Density 0.062%

    No Known Activations