© 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. 11324
    Prev
    Next
    INDEX
    Explanations

    organizational roles and operations

    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
     they
    -1.04
    ドラゴン
    -0.97
    แล้ว
    -0.97
     этими
    -0.93
    ικοί
    -0.93
     collaborators
    -0.89
    你可以
    -0.89
    Географија
    -0.89
     simplemente
    -0.88
    都有
    -0.87
    POSITIVE LOGITS
    overall
    1.02
    arching
    1.00
     geral
    0.98
     elevación
    0.97
    esthesia
    0.94
    žnost
    0.94
     daglig
    0.93
    щото
    0.91
     logistics
    0.91
     overall
    0.90
    Activations Density 0.043%

    No Known Activations