© 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. 118763
    Prev
    Next
    INDEX
    Explanations

    method calls after punctuation

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

    semicolons that terminate statements or property declarations in code.

    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
     of
    -1.42
     mixta
    -1.30
     افتراض
    -1.28
    âmetros
    -1.27
    iots
    -1.27
    anément
    -1.26
    </>
    -1.25
    linky
    -1.23
    📽
    -1.21
    鵙
    -1.21
    POSITIVE LOGITS
     It
    1.63
     it
    1.56
     according
    1.48
     noastre
    1.45
    ).
    1.42
    它
    1.42
     According
    1.39
    だそうです
    1.35
     since
    1.34
     we
    1.33
    Activations Density 0.019%

    No Known Activations