© 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. 84371
    Prev
    Next
    INDEX
    Explanations

    noun compounds

    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
     расту
    -0.94
    ");
    
    -0.92
     punkt
    -0.90
    umán
    -0.88
     Romains
    -0.87
     pstmt
    -0.87
    ENCES
    -0.87
    ˅
    -0.86
    Là
    -0.86
    )、
    -0.86
    POSITIVE LOGITS
     špec
    1.18
     specific
    1.16
     when
    1.15
    专用
    1.13
     ошибок
    1.10
     särsk
    1.05
     Rasulullah
    1.04
     stead
    1.02
     deberán
    1.02
     通信
    0.98
    Activations Density 0.091%

    No Known Activations