© 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. 9672
    Prev
    Next
    INDEX
    Explanations

    months and days

    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
     gustaba
    -1.67
     encantó
    -1.50
     くん
    -1.37
     conseiller
    -1.32
     gustó
    -1.30
     kağı
    -1.28
     verrou
    -1.26
     kolorze
    -1.26
     entret
    -1.24
     péché
    -1.23
    POSITIVE LOGITS
     and
    2.33
     which
    1.70
     of
    1.54
     которых
    1.43
     for
    1.42
     también
    1.39
     also
    1.38
    也得
    1.38
    しば
    1.27
     которого
    1.22
    Activations Density 0.352%

    No Known Activations