© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59832
    Prev
    Next
    INDEX
    Explanations

    left or right side

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

    The neuron detects tokens that specify spatial orientations or “sides” (e.g. off-side, near-side, passenger side, right hind limb).

    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
    左右
    -0.92
     bizarre
    -0.92
     craz
    -0.91
    痤
    -0.91
     algún
    -0.90
     alluring
    -0.90
     ludicrous
    -0.88
    Mouth
    -0.88
     blossoming
    -0.88
     pairs
    -0.87
    POSITIVE LOGITS
     side
    1.16
    side
    0.91
     half
    0.90
    most
    0.84
    seitig
    0.79
    恆
    0.79
     headlight
    0.79
     inferior
    0.77
    oluciones
    0.77
     wing
    0.76
    Activations Density 0.071%

    No Known Activations