© 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. 12001
    Prev
    Next
    INDEX
    Explanations

    size, count, or separators after characters

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

    the letter 's' in code contexts, particularly in variable names, command-line flags, and programming syntax.

    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
    ↵
    -1.77
     it
    -1.45
     all
    -1.38
     in
    -1.36
     just
    -1.28
     three
    -1.27
    ↵↵↵
    -1.24
     five
    -1.24
     )
    -1.24
     nine
    -1.23
    POSITIVE LOGITS
     tamaño
    1.52
     этих
    1.44
    ſſen
    1.44
    𓍊
    1.40
     Dinas
    1.40
     diesen
    1.38
    씰
    1.38
    ౧
    1.37
    サイズの
    1.36
     autonomie
    1.34
    Activations Density 0.033%

    No Known Activations