© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 14344
    Prev
    Next
    INDEX
    Explanations

    definition and code structure

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

    The neuron fires on programming identifiers—especially function, class, or command names—in code (e.g. setup, Sequential, Dense, CommandHandler).

    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
    。
    -1.88
    的
    -1.57
    After
    -1.57
    ]
    -1.54
     sostu
    -1.52
    For
    -1.50
    When
    -1.49
    Both
    -1.46
    、
    -1.45
     konten
    -1.45
    POSITIVE LOGITS
     to
    1.55
    gucig
    1.48
    });
    
    1.46
    屺
    1.45
    }];
    1.43
    )}>
    1.42
    druk
    1.42
     województwie
    1.42
    AppName
    1.42
    avajillas
    1.41
    Activations Density 0.004%

    No Known Activations