© 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. 104758
    Prev
    Next
    INDEX
    Explanations

    .com/problem/*

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

    periods following domain-related tokens (like "com" or "org") in code and URLs.

    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
     intensa
    -1.34
     nästan
    -1.32
     intenso
    -1.26
     redan
    -1.20
    Testimonials
    -1.13
    زیین
    -1.13
    sarung
    -1.10
     fortfarande
    -1.10
     famosa
    -1.09
     superfluous
    -1.09
    POSITIVE LOGITS
     is
    1.30
    </strong>
    1.29
     Luglio
    1.28
    ącz
    1.24
    君は
    1.23
     podrás
    1.20
     righe
    1.19
    縺
    1.19
     recensioni
    1.16
    沨
    1.16
    Activations Density 0.006%

    No Known Activations