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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67
    Prev
    Next
    INDEX
    Explanations

    Catalan, Italian, Czech, Latvian words

    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_10/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
    ’
    -2.55
     ganzes
    -2.23
     eigenes
    -2.17
    ビックリ
    -2.16
     те
    -2.14
    ↵
    -2.14
     plupart
    -2.11
    -”
    -2.03
     系列
    -2.02
     juncture
    -2.02
    POSITIVE LOGITS
    𖣘
    2.69
    橚
    2.48
    Odpovědět
    2.42
    秶
    2.36
    郸
    2.33
     も
    2.31
     lavoro
    2.23
    臯
    2.23
    ⌵
    2.23
     partielle
    2.22
    Activations Density 0.091%

    No Known Activations