© 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. 123698
    Prev
    Next
    INDEX
    Explanations

    code attributes and questions

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

    method chaining syntax in programming code, specifically the pattern of chaining function calls with the dot operator and method names like "append", "attr", "selectAll", and "enter".

    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
     utilizada
    -1.59
     empêcher
    -1.52
     spécifiques
    -1.50
    finally
    -1.48
     faciliter
    -1.41
    acterium
    -1.38
     (‘
    -1.37
     câteva
    -1.37
     esetén
    -1.36
    っていたので
    -1.34
    POSITIVE LOGITS
     for
    1.81
     on
    1.63
     while
    1.52
     under
    1.48
     who
    1.43
     in
    1.39
     that
    1.36
     before
    1.34
     or
    1.31
     all
    1.31
    Activations Density 0.007%

    No Known Activations