© 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. 63458
    Prev
    Next
    INDEX
    Explanations

    color singlet or octet

    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
     IV
    -0.74
     DL
    -0.72
    đu
    -0.72
     Gom
    -0.70
    å
    -0.69
    idos
    -0.67
     SSA
    -0.66
    פי
    -0.66
     ela
    -0.66
     principalmente
    -0.65
    POSITIVE LOGITS
     colour
    1.08
     color
    0.99
    farbe
    0.95
     kolor
    0.94
    Color
    0.90
    colour
    0.88
     Colour
    0.87
     COLOUR
    0.85
    color
    0.83
    COLOR
    0.82
    Activations Density 0.022%

    No Known Activations