© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72365
    Prev
    Next
    INDEX
    Explanations

    adjectives describing conditions or states

    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
    aling
    -1.57
    king
    -1.45
    ō
    -1.44
    ā
    -1.41
    cking
    -1.39
    fillment
    -1.37
    ы
    -1.35
    zied
    -1.33
    ки
    -1.31
    ely
    -1.31
    POSITIVE LOGITS
    kawasaki
    1.41
    knights
    1.38
    SaveVideo
    1.37
     penso
    1.29
    Dayton
    1.25
    красивые
    1.24
    Knights
    1.23
    也可
    1.23
    Weld
    1.23
    victoria
    1.22
    Activations Density 0.084%

    No Known Activations