© 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. 99777
    Prev
    Next
    INDEX
    Explanations

    assertion, from, testcase

    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
     or
    -1.50
    Gründe
    -1.47
     для
    -1.46
    ингл
    -1.44
     mirar
    -1.41
     mereka
    -1.36
     misalnya
    -1.35
    笄
    -1.34
    Sicher
    -1.32
    Antworten
    -1.31
    POSITIVE LOGITS
     its
    1.62
    (
    1.60
     was
    1.60
    "
    1.48
    {
    1.47
    :
    1.47
     everyone
    1.47
    eronau
    1.46
     the
    1.42
     then
    1.42
    Activations Density 0.001%

    No Known Activations