© 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. 11982
    Prev
    Next
    INDEX
    Explanations

    conjunctions and lists

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

    The neuron fires on specialized technical or scientific nouns and key domain‐specific terms.

    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
     in
    -2.20
    сыз
    -1.79
     when
    -1.77
     of
    -1.76
     estrema
    -1.75
     terbentuk
    -1.75
     the
    -1.72
     mostrare
    -1.71
     on
    -1.70
     Geruch
    -1.68
    POSITIVE LOGITS
     and
    10.94
    และ
    3.20
     และ
    3.03
     и
    2.86
     και
    2.63
     এবং
    2.50
     và
    2.42
    そして
    2.08
     And
    1.97
    力和
    1.94
    Activations Density 4.147%

    No Known Activations