© 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. 331
    Prev
    Next
    INDEX
    Explanations

    Q: or It is

    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
    is
    -1.48
     \
    -1.47
     {
    -1.45
     time
    -1.44
    身为
    -1.42
    áva
    -1.38
     my
    -1.36
    几个人
    -1.35
    ließt
    -1.34
     şi
    -1.34
    POSITIVE LOGITS
    Krankheitsbild
    1.59
    sekret
    1.57
    fährt
    1.54
    𞤢
    1.53
     soñar
    1.52
    凩
    1.52
    硨
    1.50
    köz
    1.50
    廼
    1.49
    媼
    1.46
    Activations Density 0.000%

    No Known Activations