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. 8425
    Prev
    Next
    INDEX
    Explanations

    formal beginnings and conclusions

    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
     ребят
    -1.08
     isn
    -1.07
    different
    -1.06
     guys
    -1.03
     kids
    -1.02
     บ
    -1.02
    really
    -1.01
     inside
    -1.01
     DIFFERENT
    -0.98
    ㄡ
    -0.97
    POSITIVE LOGITS
     shall
    1.44
     forthwith
    1.22
     heretofore
    1.21
     henceforth
    1.20
     glorious
    1.18
     sehr
    1.16
     весьма
    1.16
     ибо
    1.14
     hitherto
    1.13
     swiftly
    1.09
    Activations Density 0.358%

    No Known Activations