© 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. 9099
    Prev
    Next
    INDEX
    Explanations

    units of power

    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
    ↵
    -3.05
    1
    -2.89
    that
    -2.59
    2
    -2.34
    久し
    -2.33
    ’,
    -2.31
    4
    -2.30
    蹌
    -2.23
     {
    -2.20
    such
    -2.20
    POSITIVE LOGITS
    *
    2.45
    虓
    2.41
     industrielle
    2.38
    ॥
    2.38
    ll
    2.36
     hideous
    2.33
    漕
    2.28
    s
    2.27
    Ꮀ
    2.25
    滓
    2.23
    Activations Density 0.004%

    No Known Activations