© 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. 34-GEMMASCOPE-RES-131K
    7. 78447
    Prev
    Next
    INDEX
    Explanations

    throne succession inheritance crown

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

    The neuron activates on numeric tokens—especially multi‐digit numerals like years or numbered ranges.

    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
     forbidding
    -0.87
     AQUÍ
    -0.86
    闾
    -0.83
    colata
    -0.82
    apparition
    -0.80
    ('/')
    -0.80
     cavo
    -0.79
     வரு
    -0.79
     Clough
    -0.79
     vanquished
    -0.79
    POSITIVE LOGITS
     throne
    1.79
     succession
    1.36
     inheritance
    1.17
     crown
    1.17
     claimants
    1.10
     usur
    1.08
     his
    1.06
    inherits
    1.05
     ascended
    1.05
     rightful
    1.04
    Activations Density 0.054%

    No Known Activations