© 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. 12175
    Prev
    Next
    INDEX
    Explanations

    code syntax and natural language descriptions

    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
    isez
    -1.17
    ⿻
    -1.07
     suéter
    -1.07
     urządzenia
    -1.06
    AddColumn
    -1.05
    ]={
    -1.05
    EnumMember
    -1.03
     integran
    -1.01
    brador
    -0.99
     حالا
    -0.99
    POSITIVE LOGITS
     showed
    1.01
     had
    0.99
     and
    0.98
     one
    0.97
     when
    0.97
     on
    0.96
    ！！！！
    0.95
     changes
    0.93
     because
    0.91
    ė
    0.89
    Activations Density 0.000%

    No Known Activations