© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66240
    Prev
    Next
    INDEX
    Explanations

    years of existence or history

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

    The neuron responds to longer multisyllabic content words (i.e. unusually long tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     frukt
    -0.99
    因为
    -0.94
    で見る
    -0.92
    yaret
    -0.91
    oday
    -0.91
    を見ると
    -0.88
    toHave
    -0.88
    łod
    -0.88
     افزود
    -0.87
    回忆
    -0.87
    POSITIVE LOGITS
     etc
    1.23
     וכן
    1.05
    gués
    1.02
     would
    0.98
     briefly
    0.94
     sowie
    0.94
     detail
    0.94
     and
    0.93
     using
    0.93
     details
    0.93
    Activations Density 0.067%

    No Known Activations