© 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. 12329
    Prev
    Next
    INDEX
    Explanations

    preparation of, social and

    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
    ⮑
    -0.97
     jego
    -0.96
    
    -0.92
     народа
    -0.91
    ęcz
    -0.90
     século
    -0.89
     Ông
    -0.89
    ῖς
    -0.89
    étaires
    -0.87
     něj
    -0.87
    POSITIVE LOGITS
     and
    1.21
    8
    1.14
    9
    1.09
    7
    0.98
    !!!!!
    0.94
     more
    0.93
     Before
    0.93
    capai
    0.90
    قایناق
    0.90
     strongly
    0.90
    Activations Density 0.000%

    No Known Activations