© 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. 69297
    Prev
    Next
    INDEX
    Explanations

    their work or projects

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

    The neuron fires on passages describing an artist’s works being exhibited, sold, or otherwise professionally showcased.

    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
    zystać
    -1.38
    Geen
    -1.28
     itſelf
    -1.26
     obligatoire
    -1.26
     zamiast
    -1.23
    ΕΝ
    -1.20
    γα
    -1.19
    Ρ
    -1.13
    withIdentifier
    -1.13
    ichtlich
    -1.12
    POSITIVE LOGITS
     in
    1.54
     including
    1.06
    泓
    1.05
    หมือน
    1.02
     other
    1.00
    ;.
    0.99
    p
    0.96
     ngoài
    0.95
    Marke
    0.94
    ".
    0.94
    Activations Density 0.120%

    No Known Activations