© 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. 10-GEMMASCOPE-RES-131K
    7. 778
    Prev
    Next
    INDEX
    Explanations

    what happened before

    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
     first
    -2.23
     if
    -1.79
     only
    -1.71
     still
    -1.71
    ),
    -1.63
     can
    -1.62
     potential
    -1.55
     when
    -1.47
     likely
    -1.47
     both
    -1.44
    POSITIVE LOGITS
    釹
    1.65
     perles
    1.59
    跸
    1.58
    ᠁
    1.57
    を使用した
    1.55
    tabilidad
    1.52
     diamants
    1.52
    狨
    1.50
    Preparación
    1.48
    がっ
    1.47
    Activations Density 0.012%

    No Known Activations