© 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. 22014
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     moft
    -1.63
     összefoglaló
    -1.56
     estadounid
    -1.56
    🧎
    -1.48
    綃
    -1.47
    کہ
    -1.45
    Ꮂ
    -1.45
     musi
    -1.45
    <<<<
    -1.44
     alfo
    -1.44
    POSITIVE LOGITS
     will
    2.70
     now
    2.61
     not
    2.39
     about
    2.30
     new
    2.22
     use
    2.08
     may
    2.05
     can
    1.97
     see
    1.88
     first
    1.86
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.