© 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. 13249
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by content

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

    The neuron responds to closing parentheses (i.e. parenthetical expressions and their delimiters).

    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
    ifying
    -1.01
     and
    -1.01
     muur
    -1.00
    hiva
    -0.96
    ciled
    -0.95
    uuuu
    -0.94
    isierte
    -0.88
    istische
    -0.88
     மற்றும்
    -0.87
    และ
    -0.87
    POSITIVE LOGITS
     Without
    0.99
     Giving
    0.91
     debía
    0.89
    isantes
    0.88
     nurtured
    0.84
    頂いた
    0.84
    キリスト
    0.83
    avait
    0.82
     giving
    0.81
    øm
    0.80
    Activations Density 0.032%

    No Known Activations