© 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. 65886
    Prev
    Next
    INDEX
    Explanations

    landslide, avalanche, slide

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

    The neuron detects mentions of severe natural disaster events (especially flood‐ and landslide‐related terms).

    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
     сър
    -0.78
    acka
    -0.76
    hack
    -0.75
    wartz
    -0.73
     Low
    -0.73
    kunst
    -0.73
     proposée
    -0.71
    Hack
    -0.70
     瓜
    -0.69
    DDI
    -0.69
    POSITIVE LOGITS
     landslide
    2.44
     slides
    2.17
     slide
    2.13
     landslides
    2.09
    slides
    1.95
    slide
    1.91
     sliding
    1.80
     Slides
    1.70
     slid
    1.68
     avalanche
    1.68
    Activations Density 0.019%

    No Known Activations