© 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. 102273
    Prev
    Next
    INDEX
    Explanations

    closing of code blocks

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

    commas in function calls or parameter lists 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
    9
    -2.34
    These
    -2.31
    i
    -2.23
    They
    -2.08
     вони
    -2.08
    3
    -2.03
    1
    -2.02
    ２
    -1.88
    This
    -1.88
    。
    -1.88
    POSITIVE LOGITS
     continúas
    1.84
     numerosas
    1.78
    を使用した
    1.69
     撮
    1.67
     niewiel
    1.66
     It
    1.65
    </h1>
    1.65
     asimismo
    1.63
    fruta
    1.63
     utilizados
    1.59
    Activations Density 0.003%

    No Known Activations