© 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. 86760
    Prev
    Next
    INDEX
    Explanations

    branching fractions

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

    The neuron fires on highly technical experimental‐physics language—especially quantitative terms (ratios, branching fractions, CP-violation parameters, measurements, and related numerical data) characteristic of particle-physics papers.

    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
    Ind
    -0.81
    вий
    -0.76
     IND
    -0.76
    ija
    -0.75
     Banda
    -0.74
    índ
    -0.73
    シール
    -0.71
    ක
    -0.71
    medio
    -0.71
    ennom
    -0.71
    POSITIVE LOGITS
     branching
    1.49
    branch
    1.16
     Branch
    1.09
    BR
    0.92
    Branch
    0.91
     branch
    0.88
     BRANCH
    0.86
     BR
    0.84
     measured
    0.82
     Br
    0.79
    Activations Density 0.015%

    No Known Activations