© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113087
    Prev
    Next
    INDEX
    Explanations

    collecting samples

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

    scientific research methodologies involving sample collection and field observations.

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

    The neuron strongly activates on words that denote scientific data‐collection contexts—e.g. sample, collected, campaign, site, field—marking mentions of measurement or sampling events.

    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
     of
    -2.19
    ↵
    -1.67
     then
    -1.62
     not
    -1.56
     that
    -1.55
     .
    -1.41
     
    -1.38
     as
    -1.37
     no
    -1.37
    {
    -1.35
    POSITIVE LOGITS
     使っ
    1.43
    ﺅ
    1.34
    ônio
    1.30
     sociais
    1.30
    賸
    1.30
     zależności
    1.29
    翃
    1.26
    olkien
    1.24
     "";
    
    1.24
     conducted
    1.24
    Activations Density 0.146%

    No Known Activations