© 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. 104388
    Prev
    Next
    INDEX
    Explanations

    code syntax delimiters

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

    newline characters or line breaks in code, particularly after import statements, include directives, or between code blocks.

    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
    aruhi
    -1.51
    🫴
    -1.48
     Wikiseite
    -1.44
    躄
    -1.38
     podremos
    -1.37
    杁
    -1.34
    jelasan
    -1.34
     stylu
    -1.32
     haremos
    -1.31
     praktijk
    -1.30
    POSITIVE LOGITS
     It
    1.77
     These
    1.69
     it
    1.41
     Its
    1.37
    )’
    1.31
     with
    1.30
    identa
    1.30
     iaitu
    1.30
     extraordin
    1.28
    k
    1.25
    Activations Density 0.092%

    No Known Activations