© 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. 22-GEMMASCOPE-RES-131K
    7. 26577
    Prev
    Next
    INDEX
    Explanations

    with this

    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_22/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
     their
    -1.34
     those
    -1.20
     this
    -1.16
     more
    -1.10
     already
    -1.08
     people
    -1.08
     everybody
    -1.08
     automático
    -1.07
    reactstrap
    -1.05
    cestors
    -1.03
    POSITIVE LOGITS
    either
    1.14
     either
    1.06
    idiary
    1.05
     либо
    1.05
     entweder
    1.05
     beragam
    1.05
     kunjungan
    1.03
     Either
    1.00
    Rela
    0.99
     inext
    0.98
    Activations Density 0.000%

    No Known Activations