© 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. 73701
    Prev
    Next
    INDEX
    Explanations

    scoring points

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

    This neuron detects mentions of athletic performance statistics, especially expressions of numerical counts (like “four players register double‐digit kills”).

    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
    PostalCode
    -0.82
    Tort
    -0.82
     civil
    -0.81
    ēju
    -0.81
    Mund
    -0.80
    grandes
    -0.79
    xda
    -0.78
    APRIL
    -0.77
    notas
    -0.75
     recibieron
    -0.75
    POSITIVE LOGITS
     kills
    1.66
     kill
    1.62
     killing
    1.23
    kill
    1.17
    杀
    1.13
     Kills
    1.11
    Kill
    1.09
    殺
    1.07
     killed
    1.05
    KILL
    1.05
    Activations Density 0.004%

    No Known Activations