© 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. 10-GEMMASCOPE-RES-131K
    7. 112294
    Prev
    Next
    INDEX
    Explanations

    keys

    np_acts-logits-general · gemini-2.5-flash-lite

    references to locations in the Florida Keys or similar tropical/coastal geographic areas.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    gambarkan
    -1.53
     complexe
    -1.52
     autres
    -1.45
     reine
    -1.45
     hermana
    -1.42
     afs
    -1.40
     campes
    -1.35
     eene
    -1.30
     facilite
    -1.30
     solaire
    -1.30
    POSITIVE LOGITS
     mientras
    1.61
     einschließlich
    1.57
     zuerst
    1.53
     fortalecer
    1.44
     tocó
    1.39
    cloudflare
    1.38
     With
    1.38
     atraer
    1.36
     Öffentlich
    1.34
     juzgar
    1.32
    Activations Density 0.012%

    No Known Activations