© 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. 73710
    Prev
    Next
    INDEX
    Explanations

    local network configurations

    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
     about
    -1.30
     teniendo
    -1.29
     nuevos
    -1.29
     sólo
    -1.24
     centru
    -1.23
     posiblemente
    -1.22
     mientras
    -1.21
     Ruß
    -1.20
    十分的
    -1.20
     simplemente
    -1.20
    POSITIVE LOGITS
     both
    1.25
     vienas
    1.23
     with
    1.20
     båda
    1.15
     другим
    1.15
    LEVANT
    1.13
     Bedürfn
    1.13
     other
    1.12
     your
    1.12
    깎
    1.09
    Activations Density 0.150%

    No Known Activations