© 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. 26136
    Prev
    Next
    INDEX
    Explanations

    academic journals and articles

    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
     to
    -1.24
     people
    -1.13
     household
    -1.08
     сухой
    -1.04
     Attorney
    -1.04
     equipment
    -1.02
     дета
    -1.02
     retail
    -1.02
    なもの
    -1.02
    aA
    -1.02
    POSITIVE LOGITS
     oprot
    1.23
     chercheurs
    1.23
     editors
    1.23
    yorum
    1.22
    ικών
    1.20
    可爱的
    1.20
    orcid
    1.19
     journals
    1.16
     hierdie
    1.16
    معرفی
    1.16
    Activations Density 0.047%

    No Known Activations