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. 165
    Prev
    Next
    INDEX
    Explanations

    place names and topics

    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
    ,
    -1.18
     mấy
    -1.15
    ське
    -1.08
    淡淡
    -1.02
     meeste
    -1.01
    着一个
    -0.99
     The
    -0.97
    Ņ
    -0.97
    が存在
    -0.97
    си
    -0.96
    POSITIVE LOGITS
     here
    4.03
     HERE
    3.00
     aquí
    2.72
     هنا
    2.44
     здесь
    2.44
    here
    2.30
     тут
    2.14
     aqui
    2.00
     burada
    1.97
     اینجا
    1.95
    Activations Density 0.065%

    No Known Activations