© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19612
    Prev
    Next
    INDEX
    Explanations

    Alexand names, Amanita, ellipsoid, JMS, NAT, Tanzanian

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

    proper names starting with "Alexand" (like Alexander, Alexandria, Alexandru).

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

    The neuron fires strongly on tokens containing the three‐letter sequence “und” (or “and”), as in “Aman,” “Alexandr–,” and “underset.”

    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
    鲽
    -3.17
    ).
    -2.83
    觏
    -2.41
    聍
    -2.39
    厹
    -2.38
    archiwizowane
    -2.34
     главным
    -2.33
    ediakan
    -2.22
    ︓
    -2.22
    sudadera
    -2.20
    POSITIVE LOGITS
    u
    3.27
    '
    3.09
    塒
    2.78
    赂
    2.48
    year
    2.45
     BRARY
    2.44
    ar
    2.42
    </u>
    2.36
    ING
    2.34
    瓩
    2.34
    Activations Density 0.013%

    No Known Activations