© 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. 12443
    Prev
    Next
    INDEX
    Explanations

    legal facts

    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
    旆
    -1.61
     were
    -1.50
    with
    -1.50
    了不少
    -1.41
    naments
    -1.39
    着
    -1.38
    絰
    -1.38
    micos
    -1.36
    ><
    -1.33
     ähnliche
    -1.33
    POSITIVE LOGITS
    bukti
    1.46
     навіть
    1.43
     cobrar
    1.40
    ⭏
    1.36
    argentina
    1.34
    濵
    1.32
    siswa
    1.31
     Each
    1.31
     that
    1.30
     даже
    1.30
    Activations Density 0.027%

    No Known Activations