© 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. 34-GEMMASCOPE-RES-131K
    7. 87024
    Prev
    Next
    INDEX
    Explanations

    route numbers, versions, questions

    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_34/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
     Lof
    -0.79
     Amritsar
    -0.71
     outfile
    -0.70
    団
    -0.70
    Airplane
    -0.66
    荣耀
    -0.66
    TokenNameR
    -0.66
     Sully
    -0.66
    ਯ
    -0.65
     uploading
    -0.65
    POSITIVE LOGITS
     Roswell
    0.92
     crash
    0.77
    olidated
    0.77
    gemm
    0.75
     Chaves
    0.73
    ượ
    0.73
     Нью
    0.71
    gida
    0.71
    mkdirs
    0.71
     testar
    0.70
    Activations Density 0.018%

    No Known Activations