© 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. 10-GEMMASCOPE-RES-131K
    7. 123745
    Prev
    Next
    INDEX
    Explanations

    glide and acetate or extracts

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

    The neuron detects software library and technology names, particularly focusing on UI/graphics libraries like "Glide" and "JsonFormat".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    柺
    -2.55
    昞
    -2.44
    la
    -2.27
     «
    -2.27
    r
    -2.25
    跸
    -2.25
    ⧼
    -2.23
    en
    -2.22
    葶
    -2.22
    is
    -2.17
    POSITIVE LOGITS
    ’
    3.41
    --
    2.41
    ,“
    2.22
     carrés
    2.16
    '--
    2.11
    ”،
    2.09
    [
    2.09
     departamentos
    2.08
     mogen
    2.03
    𝐒
    2.03
    Activations Density 0.001%

    No Known Activations