© 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. 25573
    Prev
    Next
    INDEX
    Explanations

    default, main, standard, current, shared instances

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

    The neuron fires on Objective-C singleton accessors (e.g. defaultCenter, defaultManager, standardUserDefaults, mainScreen)

    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
    )।
    -0.95
     a
    -0.93
     Grand
    -0.89
     of
    -0.88
     such
    -0.87
     an
    -0.85
     grand
    -0.84
     by
    -0.82
     all
    -0.81
     this
    -0.81
    POSITIVE LOGITS
     PSOE
    1.00
     Lotion
    0.97
    Более
    0.94
     SiO
    0.93
    stände
    0.92
     رفتار
    0.91
     inlaid
    0.91
     Armored
    0.91
     Colegio
    0.90
     Valky
    0.90
    Activations Density 0.010%

    No Known Activations