© 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. 34-GEMMASCOPE-RES-131K
    7. 7143
    Prev
    Next
    INDEX
    Explanations

    any later version

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

    The neuron is triggered by backslash characters (i.e. escape‐sequence markers like “\” in strings).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     取付
    -0.78
     翔
    -0.77
    eriks
    -0.76
    quería
    -0.76
     carnet
    -0.75
     Mengh
    -0.75
    sers
    -0.75
     aikana
    -0.75
    нику
    -0.74
    fastjson
    -0.74
    POSITIVE LOGITS
    Address
    0.86
     address
    0.84
     memo
    0.79
    ブリッド
    0.79
    サウンド
    0.78
    有多少
    0.75
     zatr
    0.75
     getRole
    0.72
    yafet
    0.72
     Address
    0.72
    Activations Density 0.001%

    No Known Activations