© 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. 21647
    Prev
    Next
    INDEX
    Explanations

    rose and rose gold

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

    the presence of the word “rose” (in singular or plural form) in the text.

    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
     is
    -2.31
     confront
    -2.02
     dring
    -2.00
     momentous
    -1.99
     a
    -1.98
     Suitable
    -1.96
    箩
    -1.96
    好在
    -1.95
    を発見
    -1.93
    茘
    -1.93
    POSITIVE LOGITS
    ↵
    1.95
     большим
    1.92
     pájaros
    1.84
     only
    1.80
    ла
    1.78
     February
    1.72
     árbitro
    1.70
    𐑂
    1.66
     novembro
    1.66
     улыб
    1.63
    Activations Density 0.007%

    No Known Activations