© 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. 14280
    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
    。“
    -1.32
    after
    -1.21
    “
    -1.13
     out
    -1.13
    max
    -1.10
     darkest
    -1.09
    ！（
    -1.08
    现状
    -1.08
    呖
    -1.07
    UTUP
    -1.06
    POSITIVE LOGITS
     biasanya
    1.58
    鉨
    1.43
    彇
    1.35
     BEAUTIFUL
    1.35
     принял
    1.32
    donna
    1.32
    闐
    1.32
    ㍑
    1.32
    Seems
    1.32
    seems
    1.32
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.