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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1658
    Prev
    Next
    INDEX
    Explanations

    legal cases and judge names

    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
    らしいです
    -1.05
    痾
    -0.95
     sacerdotes
    -0.92
    当场
    -0.91
    俪
    -0.88
     econômica
    -0.88
     unwillingness
    -0.87
    轻易
    -0.86
    而后
    -0.85
    悝
    -0.85
    POSITIVE LOGITS
     другому
    0.98
     tänker
    0.92
     känner
    0.92
     beeintr
    0.90
     ‘‘
    0.90
     gefördert
    0.89
     berättar
    0.86
    ᄀ
    0.86
    andafter
    0.86
     Homem
    0.85
    Activations Density 0.364%

    No Known Activations