Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7984
    Prev
    Next
    INDEX
    Explanations

    devices and technologies

    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
    might
    -1.33
     gruesome
    -1.27
    奩
    -1.23
    primarily
    -1.20
    €™
    -1.18
    ฺ
    -1.17
     présents
    -1.16
     VERY
    -1.16
     THEIR
    -1.16
    為に
    -1.16
    POSITIVE LOGITS
     in
    1.61
     can
    1.57
     with
    1.52
    、
    1.44
     of
    1.41
     after
    1.29
     at
    1.18
     that
    1.16
     such
    1.12
    ,
    1.11
    Activations Density 0.148%

    No Known Activations