© 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. 30311
    Prev
    Next
    INDEX
    Explanations

    home runs

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

    The neuron activates on baseball scoring or hitting events (home runs, runs driven in, extra-base hits, 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
     mutable
    -0.84
    撬
    -0.78
    motic
    -0.76
     exclusions
    -0.75
    ningss
    -0.73
    揖
    -0.72
     tingling
    -0.71
     Händler
    -0.71
     nib
    -0.70
    itou
    -0.70
    POSITIVE LOGITS
     home
    2.22
     homer
    2.22
     Home
    2.05
     hom
    2.03
    Home
    1.86
    home
    1.78
     HOME
    1.64
    HOME
    1.62
     HOM
    1.53
     Hom
    1.52
    Activations Density 0.017%

    No Known Activations