© 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. 10-GEMMASCOPE-RES-131K
    7. 42650
    Prev
    Next
    INDEX
    Explanations

    volcanic eruption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    鸲
    -2.77
    謦
    -2.75
    憮
    -2.73
    as
    -2.67
    in
    -2.59
    玧
    -2.56
    C
    -2.56
    
    -2.53
    玙
    -2.53
    ౮
    -2.53
    POSITIVE LOGITS
    皛
    2.38
     Not
    2.30
     Как
    2.19
    乆
    2.11
     alberga
    2.09
    ,
    2.08
    
    2.03
    垕
    2.03
    亖
    1.96
     She
    1.95
    Activations Density 0.002%

    No Known Activations