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. 300
    Prev
    Next
    INDEX
    Explanations

    significant descriptors and context

    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
     recently
    -1.36
     recentemente
    -1.34
     sapi
    -1.33
     herrera
    -1.31
    </strong>
    -1.30
    λιο
    -1.29
     недавно
    -1.23
    َل
    -1.21
    cin
    -1.20
    ”?
    -1.20
    POSITIVE LOGITS
     a
    1.77
     in
    1.59
     an
    1.56
     for
    1.55
     most
    1.47
     then
    1.42
    voer
    1.40
     their
    1.38
    懺
    1.34
     postup
    1.33
    Activations Density 0.041%

    No Known Activations