© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103812
    Prev
    Next
    INDEX
    Explanations

    RSpec tests and code structure

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

    Ruby/RSpec test file structure keywords and patterns, particularly "describe", "it", "expect", "before", "context", and spec file references.

    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
     mereka
    -1.80
    珧
    -1.71
    ࿚
    -1.63
    秝
    -1.63
    ̓
    -1.61
    ୌ
    -1.58
     ด้วย
    -1.58
     เรา
    -1.54
     especialidad
    -1.53
    either
    -1.49
    POSITIVE LOGITS
    .
    2.06
     The
    1.69
    {
    1.45
    ↵↵
    1.38
    the
    1.36
    a
    1.34
    y
    1.33
    “
    1.31
    you
    1.30
    it
    1.24
    Activations Density 0.005%

    No Known Activations