© 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. 43648
    Prev
    Next
    INDEX
    Explanations

    polyclonal, on Plesionika

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

    escape sequences in programming code, particularly tab characters represented as '\t'.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     oftentimes
    -1.59
    Kemudian
    -1.58
     subsequently
    -1.56
     then
    -1.55
    推荐阅读
    -1.49
    s
    -1.48
    　　《
    -1.47
    lığı
    -1.45
     lavish
    -1.45
     duomen
    -1.44
    POSITIVE LOGITS
     you
    1.81
    .”
    1.75
     your
    1.52
     here
    1.48
    reador
    1.48
    S
    1.41
    comparable
    1.40
    É
    1.39
     ſte
    1.38
    ying
    1.36
    Activations Density 0.004%

    No Known Activations