© 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. 71689
    Prev
    Next
    INDEX
    Explanations

    straight, vanilla, basic

    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
     Ortsteil
    -1.24
    ཫ
    -1.11
     mężczy
    -1.07
     empezó
    -1.04
     setelah
    -1.03
    すっかり
    -1.02
     גע
    -1.01
     debido
    -1.01
    ་་
    -1.01
    InputStream
    -1.00
    POSITIVE LOGITS
     passenden
    1.24
    basic
    1.24
     now
    1.24
    izontal
    1.24
    either
    1.16
     then
    1.16
     soweit
    1.10
    Pontos
    1.09
    now
    1.09
     either
    1.08
    Activations Density 0.098%

    No Known Activations