© 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. 58647
    Prev
    Next
    INDEX
    Explanations

    through

    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
    Otra
    -1.77
    yaratan
    -1.74
    medriver
    -1.69
     zimowe
    -1.63
     которого
    -1.63
    氿
    -1.62
    今でも
    -1.62
     şek
    -1.59
    僕の
    -1.59
    additional
    -1.55
    POSITIVE LOGITS
     of
    1.80
     timmar
    1.66
    .”
    1.60
    咘
    1.60
     It
    1.57
    呖
    1.55
     їх
    1.54
    .‏
    1.52
     was
    1.50
     hvil
    1.46
    Activations Density 0.004%

    No Known Activations