© 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. 10-GEMMASCOPE-RES-131K
    4. 104127
    Prev
    Next
    INDEX
    Explanations

    high-throughput analysis methods

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

    technical terms and specialized vocabulary in computing, programming, and educational contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on named software products or technical tools (often with version numbers), e.g. “cPanel Pro 1.0.0 (RC1)”.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    xvii
    -1.77
    ——–
    -1.62
    洨
    -1.61
    詎
    -1.60
    龶
    -1.53
    𝗞
    -1.51
     involucrados
    -1.51
     sencillas
    -1.50
     decorado
    -1.50
     estadounidenses
    -1.50
    POSITIVE LOGITS
    </em>
    1.89
    These
    1.82
     of
    1.72
    それぞれの
    1.70
     así
    1.68
    ным
    1.59
     sekitarnya
    1.56
    This
    1.55
     sebagainya
    1.52
     not
    1.51
    Activations Density 0.113%

    No Known Activations