© 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. 130011
    Prev
    Next
    INDEX
    Explanations

    Arizona GOP Democrats

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

    This neuron responds to code identifiers that include underscores (e.g. variable or macro names containing “_”).

    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
    There
    -2.17
    It
    -2.00
    just
    -1.97
    when
    -1.96
    Also
    -1.85
    This
    -1.82
    When
    -1.82
    Another
    -1.76
     Have
    -1.76
     It
    -1.76
    POSITIVE LOGITS
     diversos
    2.02
    翆
    2.02
    翃
    1.98
     elimina
    1.92
     innumer
    1.91
    迓
    1.88
     delectable
    1.88
     ludicrous
    1.82
     magnific
    1.81
    皷
    1.80
    Activations Density 0.000%

    No Known Activations