© 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. 40139
    Prev
    Next
    INDEX
    Explanations

    legal citations preceding "F.2d"

    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
     awful
    -1.24
     from
    -1.21
     and
    -1.20
    :{
    
    -1.10
     first
    -1.08
     very
    -1.06
     different
    -1.06
    seitigen
    -1.05
     known
    -1.05
     sudadera
    -1.02
    POSITIVE LOGITS
    〜。
    1.24
     Tú
    1.06
    报记者
    1.05
     بيها
    1.02
    さらに
    1.01
    .
    0.99
    preneurship
    0.99
    ).
    0.98
    甚至
    0.96
    いません
    0.95
    Activations Density 0.013%

    No Known Activations