© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86669
    Prev
    Next
    INDEX
    Explanations

    locations and instructions

    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
     that
    -2.06
     they
    -1.74
     which
    -1.65
     cuando
    -1.62
     quando
    -1.56
     those
    -1.55
     whose
    -1.53
     when
    -1.52
    which
    -1.50
     sometimes
    -1.44
    POSITIVE LOGITS
    ции
    1.37
     supervising
    1.36
     як
    1.25
    ката
    1.23
    ⅙
    1.22
    栀
    1.20
    ंभ
    1.18
    ⅖
    1.17
    วิว
    1.15
     salle
    1.14
    Activations Density 0.008%

    No Known Activations