© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 622
    Prev
    Next
    INDEX
    Explanations

    staying in a certain state

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    angliski
    -1.70
     that
    -1.59
     entonces
    -1.56
    岁月
    -1.54
     damaligen
    -1.51
     sitten
    -1.47
    rapie
    -1.45
     Fußballspieler
    -1.45
     damals
    -1.45
     allora
    -1.45
    POSITIVE LOGITS
    ção
    1.71
     of
    1.60
    ’
    1.58
    屃
    1.51
    iz
    1.42
    j
    1.41
    6
    1.39
    }_{\
    1.38
     didn
    1.38
    2
    1.38
    Activations Density 0.014%

    No Known Activations