© 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. 12373
    Prev
    Next
    INDEX
    Explanations

    web development code snippets

    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
     Româ
    -1.04
     Bucure
    -1.03
     Svizzera
    -1.00
    mon
    -0.99
     pesquisa
    -0.97
     playing
    -0.96
     lipca
    -0.92
    llte
    -0.92
     scholarly
    -0.90
    шні
    -0.89
    POSITIVE LOGITS
     débuts
    1.16
     then
    1.13
    Halaman
    1.09
    Eerste
    1.09
    Apakah
    1.06
    Földrajzportál
    1.04
     felizes
    1.04
    DebuggerStep
    1.03
     bénéfice
    1.02
     réfrigérateur
    0.98
    Activations Density 0.006%

    No Known Activations