© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73607
    Prev
    Next
    INDEX
    Explanations

    Q: followed by colon

    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
     it
    -1.39
    際には
    -1.09
    CheckedChanged
    -1.06
     who
    -1.03
     include
    -1.03
    靭
    -1.01
     egyéb
    -1.01
    確認ください
    -0.98
    פּ
    -0.97
     montaje
    -0.97
    POSITIVE LOGITS
    smarty
    1.00
    zenden
    1.00
    liehen
    0.99
    ¹.
    0.99
    jando
    0.99
     فقط
    0.98
    accessToken
    0.97
    がありますが
    0.97
     almacenar
    0.96
     gentry
    0.96
    Activations Density 0.000%

    No Known Activations