© 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. 99891
    Prev
    Next
    INDEX
    Explanations

    initializing code 'params'

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

    This neuron activates on occurrences of the identifier “params” in code.

    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
    鲧
    -3.19
    腠
    -2.91
     脸
    -2.81
    蟊
    -2.72
    ৢ
    -2.69
    骜
    -2.67
    }*/
    -2.66
    ſſen
    -2.66
     腿
    -2.61
     股份
    -2.61
    POSITIVE LOGITS
    In
    4.41
     
    3.86
    With
    3.52
    Because
    3.52
    Not
    3.48
    There
    3.44
    After
    3.44
    \
    3.41
    Since
    3.36
    5
    3.36
    Activations Density 0.003%

    No Known Activations