© 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. 22227
    Prev
    Next
    INDEX
    Explanations

    low-cost

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

    The neuron activates on mentions of “low cost” (i.e. it detects when something is described as low-cost).

    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
    鐃
    -2.06
     ‘‘
    -2.03
    釙
    -1.99
    越來
    -1.97
    dersfield
    -1.96
    さてさて
    -1.92
    The
    -1.91
    
    -1.91
    變得
    -1.85
    ⃨
    -1.83
    POSITIVE LOGITS
     '
    2.16
    ('
    2.03
     namun
    1.92
    し
    1.90
     of
    1.89
     ('
    1.86
    й
    1.81
    畔
    1.81
     anderen
    1.80
    。"
    1.77
    Activations Density 0.008%

    No Known Activations