© 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. 67855
    Prev
    Next
    INDEX
    Explanations

    class definitions and ends

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

    The neuron fires on Objective-C declaration keywords and directives (e.g. “@interface,” “@implementation,” “@protocol,” “@class,” “@end,” etc.).

    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
     technisch
    -1.91
     agujeros
    -1.90
    鸸
    -1.88
     erhi
    -1.84
    ſſen
    -1.80
     dì
    -1.79
    
    -1.78
    ⢪
    -1.78
     BIBLIOGRAPHY
    -1.77
    ⚋
    -1.76
    POSITIVE LOGITS
    7
    2.25
    4
    2.25
    2
    2.09
    3
    2.06
    ↵
    2.06
    9
    2.05
    0
    2.03
    !
    2.02
    However
    1.97
    8
    1.97
    Activations Density 0.006%

    No Known Activations