© 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. 10-GEMMASCOPE-RES-131K
    7. 73801
    Prev
    Next
    INDEX
    Explanations

    sports championships

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

    The neuron fires strongly on the word “Championships,” i.e. sports‐event titles ending in “Championships.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    this
    -3.44
    This
    -2.58
    2
    -2.39
    或
    -2.31
    These
    -2.28
    「
    -2.27
    !"
    -2.23
    ка
    -2.22
    ında
    -2.17
    8
    -2.14
    POSITIVE LOGITS
    衚
    2.25
    觏
    2.17
    玕
    2.13
    最后由
    2.11
    ünste
    2.09
    各样的
    2.08
    但是在
    2.08
    
    2.06
    疴
    2.05
    而来
    2.03
    Activations Density 0.005%

    No Known Activations