© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42884
    Prev
    Next
    INDEX
    Explanations

    subsurface geology and energy

    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
    </h3>
    -3.03
     We
    -2.84
     mergul
    -2.44
    al
    -2.38
    this
    -2.33
    .’
    -2.33
     trabalha
    -2.30
    ’-
    -2.27
     miał
    -2.27
    ’:
    -2.27
    POSITIVE LOGITS
     précédentes
    2.52
    ization
    2.47
    Give
    2.41
    StoryboardSegue
    2.41
    :
    2.31
     ibland
    2.28
    １
    2.28
    Frequently
    2.28
    長く
    2.25
     récentes
    2.19
    Activations Density 0.007%

    No Known Activations