© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19165
    Prev
    Next
    INDEX
    Explanations

    went to

    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
    -2.16
     involucrados
    -1.77
     when
    -1.76
    quelize
    -1.74
    0
    -1.73
    ที่จะ
    -1.71
     siihen
    -1.65
     koska
    -1.63
    "
    -1.59
    🢒
    -1.59
    POSITIVE LOGITS
     into
    1.85
     to
    1.75
     out
    1.72
    哂
    1.69
    satisfies
    1.66
    नलोड
    1.66
     sogar
    1.65
    絝
    1.62
    fő
    1.59
    famous
    1.55
    Activations Density 0.056%

    No Known Activations