© 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. 34-GEMMASCOPE-RES-131K
    4. 60649
    Prev
    Next
    INDEX
    Explanations

    questions with code or logic

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

    The neuron flags chunks of Swift code—particularly common Swift keywords and API types like `let`, `guard`, `NSImage`, `URL`, `->`, etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    !
    -1.16
    );
    -0.99
    ;
    -0.93
    ();
    -0.91
     "";
    -0.91
    ];
    -0.86
    !);
    -0.85
     whatever
    -0.83
    ";
    -0.83
    了很多
    -0.79
    POSITIVE LOGITS
     then
    0.96
     where
    0.96
     _,
    0.95
    Then
    0.95
     else
    0.92
    Otherwise
    0.92
    otherwise
    0.89
     sonst
    0.88
     *,
    0.87
    else
    0.86
    Activations Density 0.005%

    No Known Activations