© 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. 34-GEMMASCOPE-RES-131K
    7. 91862
    Prev
    Next
    INDEX
    Explanations

    time and appointments

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

    The neuron responds strongly to very common English function words and short high-frequency tokens (e.g. “to,” “you,” “had,” “I,” 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
     attemp
    -0.87
    regas
    -0.84
     Tages
    -0.82
    試試
    -0.81
     gradually
    -0.81
    ormick
    -0.81
    ingt
    -0.79
    長い
    -0.79
    我覺得
    -0.78
     puțin
    -0.78
    POSITIVE LOGITS
     rush
    0.93
     afternoon
    0.93
     went
    0.92
     resultMap
    0.89
     invité
    0.88
     dinner
    0.87
     tomorrow
    0.84
     appointment
    0.83
    DISTRIB
    0.82
    送
    0.82
    Activations Density 0.001%

    No Known Activations