© 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. 119147
    Prev
    Next
    INDEX
    Explanations

    copyright and license conditions

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

    The neuron is highly sensitive to non‐word tokens (punctuation marks, symbols, and standalone numbers) rather than to ordinary letter sequences.

    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
    ☠
    -0.97
    FUENTE
    -0.92
    เหมือน
    -0.91
    数字化
    -0.87
    хими
    -0.85
     Logo
    -0.85
    BoxShadow
    -0.85
    Библи
    -0.85
    Tokenizer
    -0.83
    میزی
    -0.83
    POSITIVE LOGITS
     vyb
    0.84
    . 
    0.81
    Pilih
    0.78
    ערכת
    0.77
    qian
    0.76
     claridad
    0.76
    否
    0.76
     elegir
    0.75
    . 
    0.75
    ?<
    0.75
    Activations Density 0.001%

    No Known Activations