© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 91069
    Prev
    Next
    INDEX
    Explanations

    related to entities and their actions

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

    The neuron activates on longer, content-heavy words (typically multi-syllable nouns or verbs).

    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
    ของคุณ
    -1.09
    嗎
    -0.93
     inserted
    -0.93
     whatever
    -0.93
     algum
    -0.91
    在你
    -0.89
     downloaded
    -0.89
    APPED
    -0.88
    した
    -0.87
    Used
    -0.86
    POSITIVE LOGITS
     that
    3.94
    ที่จะ
    2.83
     to
    2.73
     που
    1.81
     possible
    1.70
     for
    1.69
     pouvant
    1.54
     expected
    1.49
     which
    1.48
     که
    1.48
    Activations Density 0.110%

    No Known Activations