© 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. 74288
    Prev
    Next
    INDEX
    Explanations

    as... as constructions

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

    The neuron consistently fires on comparative or simile constructions—especially phrases of the form “as … as” or “live up to.”

    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
    both
    -1.34
     both
    -1.28
     كري
    -1.27
    닐
    -1.22
    </i>
    -1.21
    ִּ
    -1.17
    Kedua
    -1.14
     Kedua
    -1.13
     équip
    -1.13
     också
    -1.13
    POSITIVE LOGITS
     than
    2.47
     then
    1.16
     podríamos
    1.13
    ете
    1.09
    ників
    1.08
     allows
    1.06
     enables
    1.05
     Endlich
    1.05
     as
    1.04
    áss
    1.04
    Activations Density 0.059%

    No Known Activations