© 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. 48624
    Prev
    Next
    INDEX
    Explanations

    Phoenix, Arizona

    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
    েশ
    -0.82
     shivering
    -0.78
     notorious
    -0.75
     teeming
    -0.73
    ⵍ
    -0.73
    屋外
    -0.72
    صلة
    -0.72
    ۖ
    -0.71
    塑造
    -0.71
     certaine
    -0.70
    POSITIVE LOGITS
     Phoenix
    1.68
    Phoenix
    1.63
     phoenix
    1.40
     arizona
    1.38
    phoenix
    1.30
    Rising
    1.16
     Rising
    1.16
     ARIZONA
    1.15
     Arizona
    1.13
    Arizona
    1.11
    Activations Density 0.006%

    No Known Activations