© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101896
    Prev
    Next
    INDEX
    Explanations

    steering system apparatus wheel

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

    The neuron is selectively activated by mentions of “steering” (e.g. steering systems or steering components) in the text.

    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
    -2.58
     If
    -2.53
    2
    -2.42
     않는
    -2.38
    榀
    -2.33
    uksen
    -2.30
    佧
    -2.28
    hamilan
    -2.28
     Если
    -2.27
    自己的
    -2.25
    POSITIVE LOGITS
    狆
    2.84
    骉
    2.75
    镚
    2.69
    驀
    2.58
    ”:
    2.55
    姈
    2.53
    ”-
    2.45
    
    2.45
    ”;
    2.44
     ་
    2.42
    Activations Density 0.002%

    No Known Activations