© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67157
    Prev
    Next
    INDEX
    Explanations

    OEM, friend, http

    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
     السياس
    -1.41
     съдържа
    -1.39
     бър
    -1.39
    ଵ
    -1.38
     hivyo
    -1.38
     bubuk
    -1.34
     различни
    -1.34
     karyawan
    -1.34
    暧
    -1.34
     правительства
    -1.33
    POSITIVE LOGITS
     اختلال
    1.40
     =\
    1.38
    、、
    1.37
    =\
    1.37
    ৩
    1.34
     MessageBoxIcon
    1.30
    互相
    1.30
    1
    1.30
    nible
    1.24
    ৯
    1.24
    Activations Density 0.035%

    No Known Activations