© 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. 117541
    Prev
    Next
    INDEX
    Explanations

    black colors

    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
     every
    -0.91
    _{{\
    -0.90
     five
    -0.86
     asiático
    -0.86
     during
    -0.85
     .....
    -0.84
     before
    -0.82
     as
    -0.82
    arikat
    -0.80
    onnes
    -0.77
    POSITIVE LOGITS
     BLACK
    1.05
    Black
    0.88
    black
    0.88
     Black
    0.87
     black
    0.82
     différents
    0.82
     černé
    0.82
    的黑
    0.81
    seq
    0.80
    dark
    0.79
    Activations Density 0.003%

    No Known Activations