© 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. 12052
    Prev
    Next
    INDEX
    Explanations

    conditions or applicability

    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
     &
    -1.80
    {
    -1.66
    書いた
    -1.48
     cercano
    -1.46
    ICOLON
    -1.44
     antes
    -1.41
     certificación
    -1.35
    عنی
    -1.35
    ですかね
    -1.33
    変わらず
    -1.32
    POSITIVE LOGITS
    !"
    1.63
    englanniksi
    1.62
    6
    1.58
    ']?>
    1.56
    The
    1.52
    !"
    1.51
    ICIAN
    1.47
    ܇
    1.47
    lineTo
    1.47
    。”
    1.47
    Activations Density 0.015%

    No Known Activations