© 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. 34-GEMMASCOPE-RES-131K
    7. 77119
    Prev
    Next
    INDEX
    Explanations

    code assignment context

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

    The neuron consistently lights up on programming identifiers—especially class‐ or type‐style names in CamelCase or PascalCase.

    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
     its
    -1.33
     there
    -1.22
     indeed
    -1.01
     beneath
    -0.96
     gone
    -0.96
     roleId
    -0.95
     anything
    -0.95
     sometimes
    -0.94
     really
    -0.93
    最多
    -0.93
    POSITIVE LOGITS
    excellent
    1.07
    another
    1.03
    ]}>
    0.99
    endwhile
    0.98
     similaires
    0.97
     ͡°
    0.96
    chaleco
    0.94
    </h1>
    0.94
     تعرف
    0.92
     Risiko
    0.91
    Activations Density 0.048%

    No Known Activations