© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100721
    Prev
    Next
    INDEX
    Explanations

    programming namespaces

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

    indentation or whitespace at the beginning of lines in code or structured text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on numeric literals (numbers) within code snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     groote
    -1.63
     staffel
    -1.53
    commonly
    -1.52
     eral
    -1.49
     oogen
    -1.49
     vogel
    -1.48
     hemd
    -1.45
     décider
    -1.44
    usually
    -1.42
     eene
    -1.42
    POSITIVE LOGITS
     stolet
    1.46
     after
    1.37
     using
    1.35
     find
    1.34
     queremos
    1.31
    呖
    1.30
     potentially
    1.30
     utilizamos
    1.29
     noastre
    1.28
     linguri
    1.27
    Activations Density 0.094%

    No Known Activations