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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30921
    Prev
    Next
    INDEX
    Explanations

    color names

    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_34/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
     trắng
    -1.32
     white
    -1.20
    white
    -1.16
    black
    -1.15
     blackness
    -1.13
     black
    -1.10
    WHITE
    -1.09
     whiteness
    -1.09
    白
    -1.08
     WHITE
    -1.02
    POSITIVE LOGITS
     orange
    1.49
    orange
    1.35
     Orange
    1.29
    Orange
    1.27
     оранже
    1.10
     purple
    1.05
     yellow
    1.04
     violet
    0.99
     ORANGE
    0.98
    purple
    0.97
    Activations Density 0.014%

    No Known Activations