© 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. 34-GEMMASCOPE-RES-131K
    7. 118830
    Prev
    Next
    INDEX
    Explanations

    Google docs, sheets, presentations

    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
     Downloaded
    -0.75
    espero
    -0.73
     ச
    -0.72
    downloaded
    -0.71
    xref
    -0.70
    citroen
    -0.69
     Visite
    -0.69
    牛仔
    -0.69
     Ebola
    -0.68
     dele
    -0.68
    POSITIVE LOGITS
     Google
    3.88
    Google
    3.53
     google
    3.36
    google
    3.09
    GOOGLE
    2.25
     GOOGLE
    2.08
     googled
    1.98
    谷歌
    1.95
     گو
    1.57
     Goo
    1.52
    Activations Density 0.041%

    No Known Activations