© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 79563
    Prev
    Next
    INDEX
    Explanations

    steering wheel, system, mechanism

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

    The neuron specifically detects mentions of “steering” (and its morphological variants).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ↑↑↑</
    -2.19
    垕
    -2.19
    浔
    -2.17
    d
    -2.08
     foolish
    -1.97
    ーズン
    -1.97
     mutta
    -1.95
    渽
    -1.91
     If
    -1.89
    會有
    -1.88
    POSITIVE LOGITS
    镚
    2.48
    archiwizowane
    2.33
    );
    2.31
    」(
    2.23
     konkret
    2.19
    僦
    2.19
    骉
    2.16
     ſe
    2.14
    狌
    2.13
    ),
    2.11
    Activations Density 0.007%

    No Known Activations