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. 8394
    Prev
    Next
    INDEX
    Explanations

    is or been acted upon

    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
     undertook
    -1.37
     knew
    -1.36
     wrote
    -1.29
    はなく
    -1.23
    已经
    -1.22
     threw
    -1.22
    始めた
    -1.21
     stole
    -1.18
     confirmación
    -1.17
     withdrew
    -1.16
    POSITIVE LOGITS
     taken
    1.45
     kept
    1.27
     deceit
    1.11
     lahko
    1.10
     capaces
    1.09
     גע
    1.08
     eaten
    1.06
     Terrasse
    1.03
     subjected
    1.03
     donnant
    1.02
    Activations Density 0.355%

    No Known Activations