© 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. 34-GEMMASCOPE-RES-131K
    4. 86944
    Prev
    Next
    INDEX
    Explanations

    Yii framework components

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

    The neuron is spotting code‐style symbols and tokens (e.g. punctuation, backslashes, parentheses, numbers) rather than ordinary words.

    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
    august
    -0.75
    decoder
    -0.75
    влека
    -0.72
    ὸ
    -0.70
    dots
    -0.70
    vois
    -0.69
    nthesis
    -0.67
    楝
    -0.67
    trak
    -0.66
    Bened
    -0.66
    POSITIVE LOGITS
     Papel
    0.96
     yii
    0.91
     componentes
    0.89
    rb
    0.89
    corresponding
    0.88
    components
    0.85
     Whale
    0.85
     behaviors
    0.84
     rb
    0.84
    nested
    0.84
    Activations Density 0.021%

    No Known Activations