© 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. 116495
    Prev
    Next
    INDEX
    Explanations

    when before after

    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
    骉
    -1.11
    甚至
    -1.05
    不愿
    -1.01
    isn
    -0.96
     ORIGINAL
    -0.96
     смогут
    -0.95
     подоб
    -0.94
    又一次
    -0.94
     stalwart
    -0.93
    神
    -0.93
    POSITIVE LOGITS
     When
    1.03
     Before
    0.94
    另一种
    0.91
     for
    0.91
     Untuk
    0.91
    praš
    0.88
     After
    0.88
    ﾅ
    0.88
    satunya
    0.87
     when
    0.85
    Activations Density 0.369%

    No Known Activations