© 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. 34-GEMMASCOPE-RES-131K
    7. 118451
    Prev
    Next
    INDEX
    Explanations

    update and process

    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_34/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
    glGen
    -1.23
     initial
    -1.20
     초기
    -1.18
     Initial
    -1.13
    初始化
    -1.11
     initialise
    -1.07
     Init
    -1.06
    Initial
    -1.04
     empiezan
    -1.03
     initializes
    -1.02
    POSITIVE LOGITS
     if
    1.85
     update
    1.49
    if
    1.41
    Update
    1.30
     check
    1.30
     Update
    1.24
     updates
    1.21
    update
    1.20
     updating
    1.16
    更新
    1.14
    Activations Density 0.010%

    No Known Activations