© 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. 10-GEMMASCOPE-RES-131K
    7. 100894
    Prev
    Next
    INDEX
    Explanations

    unique qualifiers

    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_10/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
    参见
    -1.54
    ————————
    -1.47
    两人
    -1.45
    ——–
    -1.45
     {
    -1.45
    )։
    -1.44
    {
    -1.44
     mutta
    -1.41
    だけど
    -1.39
    告诉你
    -1.39
    POSITIVE LOGITS
     oposición
    1.40
    റ്
    1.35
     launches
    1.32
    right
    1.31
     nación
    1.30
    ью
    1.30
     desire
    1.30
    kaner
    1.30
     erinnert
    1.29
     çelik
    1.28
    Activations Density 0.003%

    No Known Activations