© 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. 14648
    Prev
    Next
    INDEX
    Explanations

    inspired by

    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
     for
    -2.16
     or
    -1.55
    遑
    -1.47
    ificado
    -1.27
    着她
    -1.27
     untuk
    -1.20
    了一会儿
    -1.19
     as
    -1.19
     для
    -1.17
    ynthetic
    -1.15
    POSITIVE LOGITS
     both
    1.31
     other
    1.28
    fmf
    1.27
    ereka
    1.24
    Sortie
    1.23
     хочу
    1.20
     of
    1.18
     provocó
    1.17
     组合
    1.16
     ofrecerte
    1.16
    Activations Density 0.112%

    No Known Activations