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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7861
    Prev
    Next
    INDEX
    Explanations

    [noun] [group/role]

    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
    trucks
    -1.16
    :['
    -1.16
     Installer
    -1.08
    人的
    -1.07
    糧
    -1.02
     teenager
    -1.02
    buyer
    -1.02
    勇者
    -0.99
    payer
    -0.98
    諱
    -0.98
    POSITIVE LOGITS
    つづく
    1.33
     skupina
    1.25
    潆
    1.24
     една
    1.23
     obicei
    1.22
     dificuldades
    1.21
    údos
    1.20
     estatales
    1.18
     barva
    1.18
     princesas
    1.18
    Activations Density 0.317%

    No Known Activations