© 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. 11359
    Prev
    Next
    INDEX
    Explanations

    programming keywords and syntax

    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_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
    któ
    -1.42
    Jeśli
    -1.42
     tomto
    -1.32
    źródło
    -1.29
    archiw
    -1.29
     Ön
    -1.29
    oneof
    -1.29
    zdo
    -1.28
    اغ
    -1.28
    sprzed
    -1.27
    POSITIVE LOGITS
    d
    1.37
    で
    1.35
    u
    1.34
    z
    1.29
    na
    1.29
    b
    1.27
    ce
    1.26
    van
    1.26
    per
    1.25
    da
    1.23
    Activations Density 0.004%

    No Known Activations