© 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. 34819
    Prev
    Next
    INDEX
    Explanations

    technical, scientific, formal contexts

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

    This neuron responds strongly to low-frequency, often longer or domain-specific tokens (e.g. uncommon words, technical terms, and numbers).

    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
     notwendi
    -0.66
     TAN
    -0.66
     Oblig
    -0.66
     start
    -0.66
    ολ
    -0.65
     two
    -0.65
     двох
    -0.64
    کن
    -0.64
     Effec
    -0.63
    Tv
    -0.63
    POSITIVE LOGITS
    live
    0.83
     présentent
    0.73
    ginate
    0.70
     estrictamente
    0.66
    IgnoreCase
    0.65
     qualidade
    0.64
     anni
    0.64
     fem
    0.64
    äischen
    0.64
    quality
    0.63
    Activations Density 0.087%

    No Known Activations