© 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. 19847
    Prev
    Next
    INDEX
    Explanations

    Surgical treatment

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

    programming and technical terms, particularly related to software code and mathematical expressions.

    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
     biała
    -1.25
     rozpoczę
    -1.22
     weiterer
    -1.17
    ことができます
    -1.17
     Bedarf
    -1.15
     schlafen
    -1.15
    就是这样
    -1.13
    該当
    -1.12
     zpě
    -1.12
     helyez
    -1.09
    POSITIVE LOGITS
     gamle
    1.43
     friv
    1.40
     tulis
    1.39
     tien
    1.37
     yng
    1.37
    غير
    1.36
     samti
    1.36
     to
    1.36
     naturen
    1.36
     laki
    1.35
    Activations Density 0.002%

    No Known Activations