© 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. 79179
    Prev
    Next
    INDEX
    Explanations

    hexadecimal color codes

    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
     black
    -1.68
    black
    -1.41
    黑
    -1.29
    BLACK
    -1.27
    黒
    -1.24
     BLACK
    -1.23
     سیاه
    -1.19
    Black
    -1.17
     dark
    -1.16
     blackness
    -1.16
    POSITIVE LOGITS
     pastel
    1.28
     peach
    1.07
     Bondi
    0.97
     mint
    0.94
     pastels
    0.94
    Pastel
    0.92
    Pink
    0.89
     pink
    0.88
     sky
    0.88
     Powder
    0.87
    Activations Density 0.023%

    No Known Activations