© 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. 2695
    Prev
    Next
    INDEX
    Explanations

    court preceding numbers or names

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

    The neuron strongly activates on numeric tokens (years, dates, percentages, counts, 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_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
     بعد
    -0.96
     всё
    -0.91
    dropIfExists
    -0.90
    PRESA
    -0.85
    resos
    -0.85
     gabbana
    -0.84
    RICAL
    -0.83
    <h3>
    -0.83
     tienes
    -0.82
    hette
    -0.82
    POSITIVE LOGITS
     source
    1.32
     sources
    1.06
    sources
    1.01
    ource
    0.97
    source
    0.93
    щество
    0.89
     advices
    0.89
    ೃ
    0.87
    ㅋㅋ
    0.87
     PRIME
    0.87
    Activations Density 0.028%

    No Known Activations