© 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. 116600
    Prev
    Next
    INDEX
    Explanations

    earthquake depth USGS

    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_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
    文明
    -0.82
    ừ
    -0.73
     твор
    -0.72
     Andromeda
    -0.72
     enabled
    -0.72
     out
    -0.72
     from
    -0.70
    Enabled
    -0.69
    Clik
    -0.69
    זה
    -0.69
    POSITIVE LOGITS
     Depth
    1.06
     shallow
    0.98
    shallow
    0.98
    chaleco
    0.93
    Shallow
    0.91
     depth
    0.90
    erda
    0.87
     USGS
    0.87
    bluza
    0.86
    DEPTH
    0.85
    Activations Density 0.007%

    No Known Activations