© 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. 34-GEMMASCOPE-RES-131K
    4. 118169
    Prev
    Next
    INDEX
    Explanations

    from ... to .

    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_34/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
    减肥
    -1.07
    けどね
    -1.07
    不喜欢
    -1.06
    不愿意
    -1.02
     knowled
    -1.00
     technisch
    -0.99
     precipitated
    -0.98
    シルエット
    -0.98
     proveniente
    -0.97
    机的
    -0.95
    POSITIVE LOGITS
     लेकर
    1.24
     until
    1.16
     During
    1.15
    _;
    
    1.10
     This
    1.08
    کنون
    1.07
    тельность
    1.02
     around
    1.01
    *}
    
    1.00
     without
    0.97
    Activations Density 0.040%

    No Known Activations