© 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. 130279
    Prev
    Next
    INDEX
    Explanations

    change the world

    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
    為に
    -1.62
    ようです
    -1.49
    فقط
    -1.42
     jotka
    -1.35
     whoſe
    -1.32
    きち
    -1.30
     leaſt
    -1.28
    マジで
    -1.27
    是什麼
    -1.27
    際は
    -1.27
    POSITIVE LOGITS
    などを
    1.78
     by
    1.77
     with
    1.74
    を
    1.58
     to
    1.40
    などは
    1.39
    品種
    1.34
    も
    1.33
    風味
    1.30
    が
    1.30
    Activations Density 0.049%

    No Known Activations