© 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. 33216
    Prev
    Next
    INDEX
    Explanations

    informing or notifying

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

    The neuron activates on verbs that describe alerting or notifying people (e.g. informed, notified, warn, warns).

    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
     for
    -0.94
     beschäftigt
    -0.83
     recommendation
    -0.83
    からです
    -0.81
     capacidade
    -0.81
     loamy
    -0.78
     vanligt
    -0.78
    들을
    -0.77
     faktiskt
    -0.77
    वी
    -0.75
    POSITIVE LOGITS
     of
    3.17
     about
    1.93
     via
    1.60
    一声
    1.45
     that
    1.39
     bahwa
    1.16
    шаго
    1.16
     when
    1.13
    via
    1.13
     vía
    1.13
    Activations Density 0.028%

    No Known Activations