© 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. 22-GEMMASCOPE-RES-131K
    7. 40100
    Prev
    Next
    INDEX
    Explanations

    AstraZeneca

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

    indentation spaces before asterisks in code comments.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires strongly on long runs of leading whitespace (indentation) at the start of lines.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     more
    -1.33
     its
    -1.14
    providedIn
    -1.09
    //}
    -0.98
     full
    -0.97
     cautious
    -0.94
     begin
    -0.94
     out
    -0.94
     Create
    -0.94
     by
    -0.93
    POSITIVE LOGITS
     acepción
    1.11
     bildet
    1.09
    也可以
    1.08
    artigen
    1.05
    大丈夫です
    1.05
    LikeLiked
    1.04
     geprü
    1.02
     которые
    1.02
     asistir
    1.02
    would
    1.01
    Activations Density 0.000%

    No Known Activations