© 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. 130923
    Prev
    Next
    INDEX
    Explanations

    hot temperature or condition

    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
     
    -2.81
    of
    -2.78
    ed
    -2.58
    able
    -2.41
    m
    -2.36
    (
    -2.31
    u
    -2.30
      
    -2.25
    ive
    -2.19
    だら
    -2.19
    POSITIVE LOGITS
    ꜆
    2.52
    ADUATE
    2.48
     馆
    2.28
    หรือ
    2.27
     lepší
    2.23
     justifiable
    2.22
    銠
    2.20
     szybko
    2.16
    tedì
    2.14
    庭園
    2.11
    Activations Density 0.006%

    No Known Activations