© 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. 98627
    Prev
    Next
    INDEX
    Explanations

    `=` followed by key or value

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

    The neuron fires on backslash‐escaped quotation marks (i.e. the “\"” escape sequence) in the text.

    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
    1
    -4.00
    0
    -3.84
    3
    -3.27
    2
    -2.95
    𖥦
    -2.92
    4
    -2.91
    6
    -2.91
    8
    -2.89
    7
    -2.80
    5
    -2.67
    POSITIVE LOGITS
     desarroll
    3.02
    蓠
    2.92
    龊
    2.91
    逦
    2.83
    場に
    2.81
    に使
    2.80
     estándares
    2.70
    珵
    2.67
    睃
    2.53
    ‗
    2.50
    Activations Density 0.016%

    No Known Activations