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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 97767
    Prev
    Next
    INDEX
    Explanations

    Spice Girls and girl groups

    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
     pecados
    -0.83
     büyü
    -0.82
    knit
    -0.77
    стасия
    -0.75
    ocratic
    -0.75
     organización
    -0.73
    husky
    -0.72
    蓁
    -0.72
    nesty
    -0.71
    fili
    -0.71
    POSITIVE LOGITS
     Spice
    1.30
    Spice
    1.06
     spice
    0.91
     Spices
    0.85
    spice
    0.83
    Objectives
    0.82
     Scary
    0.82
     powers
    0.78
     Powers
    0.77
     Austin
    0.74
    Activations Density 0.008%

    No Known Activations