© 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. 105474
    Prev
    Next
    INDEX
    Explanations

    list processing in code

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

    whitespace indentation at the beginning of lines in 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
    a
    -2.34
    .
    -2.33
     nosso
    -2.28
     notre
    -2.08
    </h1>
    -2.03
    us
    -2.00
    檍
    -1.98
    骓
    -1.98
     drugi
    -1.97
    divarius
    -1.95
    POSITIVE LOGITS
    平常
    2.20
    賔
    2.09
    衚
    2.02
     飯店
    1.89
     لأن
    1.89
    ⑊
    1.88
     spannende
    1.87
     maravillosas
    1.86
     africains
    1.84
    鶲
    1.79
    Activations Density 0.011%

    No Known Activations