© 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. 34-GEMMASCOPE-RES-131K
    7. 59143
    Prev
    Next
    INDEX
    Explanations

    upright, erect, straightened

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

    The neuron detects words referring to vertical orientation or being upright (e.g., “bolt upright,” “vertically,” “sitting up”).

    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
     Crowe
    -0.82
    начала
    -0.79
    JvmStatic
    -0.77
     druž
    -0.76
     résoudre
    -0.68
    Strepto
    -0.68
    hnung
    -0.67
     מקום
    -0.67
    čku
    -0.66
    domada
    -0.65
    POSITIVE LOGITS
     upright
    4.94
     erect
    3.19
    pright
    2.83
     вертика
    2.08
     vertical
    2.06
     straight
    1.98
     straighten
    1.98
     straightened
    1.91
     straightening
    1.85
    straight
    1.80
    Activations Density 0.050%

    No Known Activations