© 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. 98426
    Prev
    Next
    INDEX
    Explanations

    volcanoes, eruptions, volcanology, volcanism

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

    The neuron strongly activates on terminology related to volcanic activity (e.g., “Krakatoa,” “explosion,” “volcano,” “volcanic,” “eruption”).

    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
    おま
    -0.84
    
    -0.81
    karz
    -0.77
    inium
    -0.77
    siella
    -0.76
     resistances
    -0.75
     সা
    -0.75
    athy
    -0.75
    össä
    -0.75
    STELL
    -0.75
    POSITIVE LOGITS
     volcano
    2.80
     eruption
    2.44
     volcanoes
    2.27
     volcanic
    2.27
     eruptions
    2.16
     Volcano
    2.11
     volcan
    2.06
     erup
    1.80
    🌋
    1.77
     erupted
    1.76
    Activations Density 0.022%

    No Known Activations