© 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. 101891
    Prev
    Next
    INDEX
    Explanations

    keys and values

    np_acts-logits-general · gemini-2.5-flash-lite

    object property or attribute access patterns in code, particularly when accessing the "name", "type", "id", or "data" properties.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     nieuwe
    -1.48
     étages
    -1.39
     preuves
    -1.36
    りました
    -1.34
     новые
    -1.30
     that
    -1.28
    냈
    -1.27
     mereka
    -1.26
     yourself
    -1.25
     trajets
    -1.25
    POSITIVE LOGITS
     then
    1.53
     can
    1.45
     has
    1.40
     could
    1.38
    when
    1.30
    Sonstiges
    1.28
    When
    1.22
     pasará
    1.21
     quedará
    1.21
     debió
    1.20
    Activations Density 0.018%

    No Known Activations