© 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. 22-GEMMASCOPE-RES-131K
    7. 67893
    Prev
    Next
    INDEX
    Explanations

    quantity

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

    The neuron fires on occurrences of the word “quantity.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     übri
    -2.63
    mbgg
    -2.58
     schönes
    -2.45
     glän
    -2.45
     schicken
    -2.39
     nonchal
    -2.38
     unglaub
    -2.38
     jeopardi
    -2.34
    jaqueta
    -2.33
     exclusivamente
    -2.31
    POSITIVE LOGITS
    笄
    2.48
    蝙
    2.38
     signifikan
    2.36
    </em>
    2.34
    .
    2.33
    isations
    2.25
     liberté
    2.25
    ֟
    2.23
    呖
    2.22
    ?
    2.20
    Activations Density 0.015%

    No Known Activations