© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12310
    Prev
    Next
    INDEX
    Explanations

    start of file headers

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

    encoded or cryptographic strings, particularly base64-encoded data and API keys.

    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
     has
    -2.41
     could
    -2.33
     first
    -2.33
     began
    -2.31
     should
    -2.27
     taking
    -2.27
     took
    -2.25
     demonstrates
    -2.11
     despite
    -2.08
     prevents
    -2.08
    POSITIVE LOGITS
    鵙
    2.34
    裥
    2.14
     consommate
    2.14
     trône
    2.05
    𓆏
    2.02
     エッチ
    2.00
     estadounid
    1.97
     egreg
    1.91
     Reſ
    1.91
     Eſ
    1.90
    Activations Density 0.027%

    No Known Activations