© 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. 22-GEMMASCOPE-RES-131K
    7. 130411
    Prev
    Next
    INDEX
    Explanations

    legal case suffixes and titles

    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
     question
    -0.94
     दिल्ली
    -0.83
     veröffentlich
    -0.82
     kreuz
    -0.79
    ρύ
    -0.78
     Frage
    -0.77
    ༄
    -0.76
    ↵↵↵
    -0.75
    杆
    -0.75
    犼
    -0.74
    POSITIVE LOGITS
    zni
    0.84
     蕾
    0.82
     dårlig
    0.81
     stø
    0.80
     rağmen
    0.79
     søndag
    0.79
     långt
    0.79
    ㄕ
    0.79
    nowy
    0.79
     länge
    0.79
    Activations Density 0.071%

    No Known Activations