© 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. 128298
    Prev
    Next
    INDEX
    Explanations

    abbreviations followed by context

    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
    amplific
    -1.47
     sév
    -1.37
    comand
    -1.37
    escar
    -1.35
     delitos
    -1.35
     habitantes
    -1.34
    calça
    -1.32
    igreja
    -1.32
    empres
    -1.31
    emporio
    -1.31
    POSITIVE LOGITS
     DUAL
    1.34
     Sovi
    1.32
     turg
    1.31
    ❕
    1.30
     Sitio
    1.29
    🌟
    1.28
    .
    1.27
     prestation
    1.27
     ronde
    1.24
     Liège
    1.22
    Activations Density 0.173%

    No Known Activations