© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44127
    Prev
    Next
    INDEX
    Explanations

    jump

    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
     This
    -2.72
    顷
    -2.50
     vollständige
    -2.34
    ☑️
    -2.31
     analyse
    -2.28
     französische
    -2.25
     adanya
    -2.20
    and
    -2.20
    骤
    -2.20
     menyebabkan
    -2.19
    POSITIVE LOGITS
     ſta
    3.09
    歃
    2.94
     köln
    2.75
     valentín
    2.70
    澌
    2.59
    橚
    2.55
     creada
    2.45
     intellectuelle
    2.42
    ⬮
    2.41
    锱
    2.41
    Activations Density 0.005%

    No Known Activations