© 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. 31496
    Prev
    Next
    INDEX
    Explanations

    Sun and sun-starting compounds

    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
    rode
    -0.74
    genie
    -0.71
    dj
    -0.70
    zigen
    -0.69
    Fails
    -0.69
    tales
    -0.69
     vlož
    -0.68
    Laughs
    -0.67
     Nunes
    -0.67
    thew
    -0.67
    POSITIVE LOGITS
     Sun
    1.45
    Sun
    1.41
     太陽
    1.25
    beam
    1.21
    rays
    1.12
     rays
    1.05
     SUN
    1.04
     sun
    1.02
     Tzu
    1.02
    ray
    1.00
    Activations Density 0.016%

    No Known Activations