© 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. 10-GEMMASCOPE-RES-131K
    4. 90573
    Prev
    Next
    INDEX
    Explanations

    quotes and punctuation

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

    The neuron is triggered by quotation‐mark characters (i.e. text opening or closing quotes).

    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
    ﮕ
    -2.53
    Elaboración
    -2.06
    っす
    -2.05
     同人
    -1.99
     CAMPAIGN
    -1.93
    )」
    -1.92
     BRAZIL
    -1.91
     ولكن
    -1.91
     BIRDS
    -1.91
     PUBL
    -1.89
    POSITIVE LOGITS
    ?
    2.80
    actéristi
    2.72
    >
    2.56
     they
    2.55
    荭
    2.33
    "
    2.23
    :
    2.06
    ]
    1.98
    <
    1.96
      
    1.94
    Activations Density 0.008%

    No Known Activations