© 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. 103580
    Prev
    Next
    INDEX
    Explanations

    facilitate or connect

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

    The neuron highlights prominent domain‐specific technical keywords—i.e. singular nouns that name the core concepts or "switches" in a passage.

    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
     including
    -1.29
     how
    -1.04
     așa
    -0.98
     this
    -0.97
     massima
    -0.93
     another
    -0.93
     partea
    -0.91
    mar
    -0.90
    有一個
    -0.90
    using
    -0.89
    POSITIVE LOGITS
     for
    1.95
     of
    1.45
     для
    1.40
     bagi
    1.30
     både
    1.29
    вѣ
    1.27
     للمعارف
    1.27
    tothe
    1.25
     dorados
    1.23
     capable
    1.22
    Activations Density 0.120%

    No Known Activations