© 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. 104586
    Prev
    Next
    INDEX
    Explanations

    python script beginnings

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

    the first newline or indentation immediately following a Python shebang line.

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

    This neuron fires on the special “# ! /​usr/​bin/​env python” shebang line that marks the start of a Python script (and similar standalone section‐header 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_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
    僰
    -2.06
    %;
    
    -2.00
    糴
    -1.97
     夜景
    -1.96
    艄
    -1.93
    Helping
    -1.91
    argento
    -1.91
    脔
    -1.88
    ichtete
    -1.88
     prace
    -1.86
    POSITIVE LOGITS
     which
    2.30
    b
    2.20
     on
    1.98
     at
    1.86
     parezca
    1.80
     can
    1.74
     from
    1.73
     to
    1.72
     in
    1.64
     and
    1.64
    Activations Density 0.002%

    No Known Activations