© 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. 47732
    Prev
    Next
    INDEX
    Explanations

    acetyl-followed by chemical names

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

    court document headers and legal case formatting.

    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
    er
    -2.97
    1
    -2.69
    "
    -2.48
    *
    -2.45
    щиеся
    -2.25
     necessarily
    -2.25
    狁
    -2.09
     Brought
    -2.06
    A
    -1.92
     Затем
    -1.88
    POSITIVE LOGITS
    ﯼ
    2.80
    خوب
    2.53
    llten
    2.42
    臜
    2.39
    вгений
    2.38
     encantó
    2.34
    茕
    2.31
    寕
    2.31
     ultimi
    2.30
     είναι
    2.28
    Activations Density 0.012%

    No Known Activations