© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1753
    Prev
    Next
    INDEX
    Explanations

    Sunny or Sonny names, places, or weather

    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
    support
    -1.07
    SUPPORT
    -1.05
     supported
    -1.00
     support
    -0.96
     soporte
    -0.95
     supports
    -0.94
     supporting
    -0.93
     SUPPORT
    -0.91
     Supports
    -0.89
    supporting
    -0.88
    POSITIVE LOGITS
     disposition
    1.20
     side
    1.14
     uplands
    1.02
    side
    0.97
    Side
    0.96
     skies
    0.96
     spells
    0.94
    🌞
    0.93
    vale
    0.89
     days
    0.89
    Activations Density 0.011%

    No Known Activations