Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12124
    Prev
    Next
    INDEX
    Explanations

    variable assignment continuation

    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
    ⢀
    -0.85
    IMPLEMENTATION
    -0.84
    ВЕ
    -0.81
    hydrated
    -0.80
     DOCUMENT
    -0.78
     практики
    -0.75
    Timers
    -0.74
     Marcin
    -0.73
    YSIS
    -0.72
    Implementation
    -0.72
    POSITIVE LOGITS
     NULL
    0.89
     null
    0.81
     tried
    0.80
    jarah
    0.79
     alternative
    0.77
    andangan
    0.77
     anyhow
    0.77
     Absence
    0.77
    FormTagHelper
    0.76
    kfree
    0.76
    Activations Density 0.010%

    No Known Activations