© 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. 11321
    Prev
    Next
    INDEX
    Explanations

    United States

    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
     in
    -1.27
     by
    -0.96
     one
    -0.95
     fama
    -0.94
     can
    -0.92
     all
    -0.91
     contagios
    -0.91
     Though
    -0.90
    pography
    -0.90
    zoic
    -0.90
    POSITIVE LOGITS
     srdce
    1.17
    rocław
    1.02
    嚭
    1.02
     ameste
    1.00
    ritten
    0.96
    下さ
    0.96
    problemas
    0.96
     lleno
    0.94
    สถาน
    0.94
     kobiet
    0.94
    Activations Density 0.077%

    No Known Activations