© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11723
    Prev
    Next
    INDEX
    Explanations

    importing code modules

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

    forward slashes in file paths or import statements in code.

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

    This neuron detects tokens from file path strings—particularly the directory separators (slashes) and surrounding path segments in import/include statements.

    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
     for
    -1.95
     on
    -1.84
     otros
    -1.64
     для
    -1.55
    常に
    -1.52
    るのは
    -1.52
    ของ
    -1.51
    LayoutConstraint
    -1.51
     även
    -1.50
     også
    -1.49
    POSITIVE LOGITS
     которы
    1.66
     whofe
    1.62
     fhort
    1.59
    䊏
    1.58
     negru
    1.53
     feveral
    1.52
    sandalia
    1.52
     rhein
    1.52
     attempts
    1.51
     linf
    1.51
    Activations Density 0.007%

    No Known Activations