© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13618
    Prev
    Next
    INDEX
    Explanations

    abundance is, supply last, latter than

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

    The neuron activates on multi‐word phrases that describe quantity or degree (e.g. abundance, scarcity, “lots of,” “range of,” “valuable commodity”).

    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
     will
    -1.35
     would
    -1.22
     contactez
    -1.13
    phor
    -1.08
     intval
    -1.06
    strando
    -1.06
    taxia
    -1.05
     if
    -1.04
    бята
    -1.03
    дем
    -1.02
    POSITIVE LOGITS
     discussed
    1.44
    ene
    1.34
     zaidi
    1.30
     nejen
    1.21
     these
    1.16
    discussed
    1.16
     ndani
    1.15
     durante
    1.14
    definitely
    1.14
     kutoka
    1.13
    Activations Density 0.029%

    No Known Activations