© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 12120
    Prev
    Next
    INDEX
    Explanations

    code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     thingy
    -1.22
    ᐳ
    -1.21
     ulica
    -1.21
     extraordinaire
    -1.20
    挙げ
    -1.16
    齟
    -1.10
     sensation
    -1.09
     retten
    -1.08
     ویکی‌پدیا
    -1.06
    りましたが
    -1.06
    POSITIVE LOGITS
     noqa
    1.58
     <--
    1.48
    etches
    1.38
     omfatt
    1.30
     necesario
    1.28
     понадобится
    1.28
    お楽しみに
    1.27
     <-
    1.27
    的花
    1.26
    !<
    1.24
    Activations Density 0.036%

    No Known Activations