© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11330
    Prev
    Next
    INDEX
    Explanations

    academic research and journals

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

    academic journal and publication titles.

    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_22/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
     teka
    -1.42
    tarif
    -1.39
    materi
    -1.30
     yaka
    -1.27
     quedaba
    -1.23
     kutu
    -1.21
    grafik
    -1.20
     概要
    -1.18
    Transk
    -1.17
     jawab
    -1.14
    POSITIVE LOGITS
    madi
    1.13
    哪儿
    1.06
     (
    1.02
    each
    1.00
    торами
    0.99
     -
    0.98
     bares
    0.97
    咱们
    0.97
     zirconia
    0.96
     Branson
    0.95
    Activations Density 0.006%

    No Known Activations