© 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. 119650
    Prev
    Next
    INDEX
    Explanations

    string manipulation and indexing

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

    closing brackets or parentheses in array indexing and slicing operations.

    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
     no
    -1.39
     Erkrank
    -1.29
    IN
    -1.25
     importanti
    -1.22
    if
    -1.21
     final
    -1.19
    AT
    -1.18
    add
    -1.17
     très
    -1.16
     \
    -1.16
    POSITIVE LOGITS
     včetně
    1.53
    etna
    1.29
    سجيل
    1.27
    𝒒
    1.27
    pueden
    1.23
     everytime
    1.22
     sooooo
    1.21
    sians
    1.20
     które
    1.20
    Bienvenido
    1.19
    Activations Density 0.008%

    No Known Activations