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. 8260
    Prev
    Next
    INDEX
    Explanations

    website and clearance codes

    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
    ervative
    -1.16
    prada
    -1.11
    chom
    -1.09
    waffle
    -1.09
     kleinere
    -1.09
     zubehör
    -1.08
    rolex
    -1.08
     nacidos
    -1.07
     technisch
    -1.07
     този
    -1.07
    POSITIVE LOGITS
    Чтобы
    1.21
    info
    1.06
    영어
    1.05
    Pilih
    1.02
     info
    1.02
     want
    1.02
    τηση
    1.01
     misteriosa
    1.01
     or
    1.00
     besonders
    1.00
    Activations Density 0.046%

    No Known Activations