© 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. 103804
    Prev
    Next
    INDEX
    Explanations

    Code row structuring

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

    the word "row" in programming code contexts, particularly when used as a variable name or object property.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     條
    -2.33
    },
    -2.17
     There
    -2.05
     haven
    -1.99
    ],
    -1.98
     you
    -1.95
    饪
    -1.89
    ”,
    -1.83
     started
    -1.82
    .
    -1.82
    POSITIVE LOGITS
     ingenuity
    2.02
    氽
    1.95
     mereka
    1.94
     開封
    1.92
    灕
    1.91
    I
    1.91
    睺
    1.88
    鷓
    1.86
    dée
    1.84
    蕖
    1.79
    Activations Density 0.024%

    No Known Activations