© 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. 111831
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

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

    HTML/XML heading tags or comment blocks that introduce or begin sections of structured documents.

    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
     if
    -2.23
     only
    -2.00
     to
    -1.95
     și
    -1.78
     both
    -1.73
     you
    -1.62
     in
    -1.55
     this
    -1.54
    }$,
    -1.49
     just
    -1.43
    POSITIVE LOGITS
     ……
    1.66
     .......
    1.64
     بعد
    1.63
     trots
    1.59
     ........
    1.58
    about
    1.58
     пять
    1.55
     leaſt
    1.51
    …………
    1.51
    他们
    1.51
    Activations Density 0.000%

    No Known Activations