© 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. 10-GEMMASCOPE-RES-131K
    7. 70291
    Prev
    Next
    INDEX
    Explanations

    heat loss, energy loss

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

    This neuron detects occurrences of the word “loss” (and its forms like “lost” or “losses”).

    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
    In
    -1.43
    蛧
    -1.35
     then
    -1.33
    Then
    -1.30
    seros
    -1.26
    providedIn
    -1.24
    pektive
    -1.23
    今朝
    -1.23
    　　「
    -1.20
    奇跡
    -1.20
    POSITIVE LOGITS
     from
    1.48
    2
    1.30
    FINALLY
    1.30
    ignements
    1.30
    Thx
    1.26
    Warum
    1.26
    LOSS
    1.25
     enquanto
    1.22
     rempliss
    1.21
     déplo
    1.20
    Activations Density 0.068%

    No Known Activations