© 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. 103119
    Prev
    Next
    INDEX
    Explanations

    arylene, aryloxy, oryzae, arylsulfatase, sabalenka

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

    words beginning with "ary" or containing chemical/scientific prefixes.

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

    The neuron activates on the character sequence “ary” (in any casing) appearing within words.

    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
    雳
    -2.50
    𓆜
    -2.42
    嚅
    -2.25
    撺
    -2.23
    
    -2.16
     essentiellement
    -2.14
    tona
    -2.13
    u
    -2.09
    ma
    -2.09
    ł
    -2.08
    POSITIVE LOGITS
     sebagainya
    2.38
    {
    2.28
    </h2>
    2.27
     ensures
    2.06
     provides
    2.05
     emphasizes
    2.00
     suggests
    1.93
     begins
    1.91
     examines
    1.91
    </em>
    1.88
    Activations Density 0.001%

    No Known Activations