© 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. 35078
    Prev
    Next
    INDEX
    Explanations

    Q: questions

    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
     that
    -1.83
     when
    -1.29
     to
    -1.18
     That
    -1.06
     which
    -1.05
     když
    -1.03
    的一声
    -1.01
    ですか
    -0.97
    ôtel
    -0.96
     before
    -0.96
    POSITIVE LOGITS
    
    1.21
     élar
    1.17
    Kedves
    1.16
    7
    1.16
    Поздрав
    1.14
    もうすぐ
    1.13
     [].
    1.13
    久しぶりの
    1.13
    If
    1.12
    一気に
    1.12
    Activations Density 0.001%

    No Known Activations