© 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. 115582
    Prev
    Next
    INDEX
    Explanations

    sports, competitions, and achievements

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

    The neuron strongly activates on tokens referring to pinball or pachinko–style gaming (e.g. “Pin,” “ball,” “Pachinko,” “machines,” 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
     continuance
    -0.75
    ggbb
    -0.71
    псо
    -0.69
    结论
    -0.68
    removeChild
    -0.68
    diffs
    -0.68
     diploma
    -0.68
     Covered
    -0.67
    lore
    -0.64
    tiara
    -0.64
    POSITIVE LOGITS
     Suzanne
    0.83
    通用
    0.81
    Suzanne
    0.81
     pulsed
    0.80
    ∩
    0.79
     senator
    0.75
     fli
    0.75
    BX
    0.72
    pstmt
    0.71
    フリー
    0.71
    Activations Density 0.022%

    No Known Activations