© 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. 63710
    Prev
    Next
    INDEX
    Explanations

    Spartanburg

    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
     apport
    -0.78
     largement
    -0.78
    ėd
    -0.76
    が開
    -0.75
     Publicado
    -0.75
    掸
    -0.74
     Futuro
    -0.72
    ặn
    -0.71
    動物園
    -0.71
    冴
    -0.71
    POSITIVE LOGITS
     Spartan
    1.57
     Spartans
    1.45
    Spartan
    1.27
     Sparta
    1.23
    Ago
    1.02
     Spart
    0.99
    Sparta
    0.99
     spartan
    0.96
    𝕔
    0.89
     Pelop
    0.87
    Activations Density 0.005%

    No Known Activations