© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104622
    Prev
    Next
    INDEX
    Explanations

    words starting with Aqu

    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
     Of
    -2.78
    6
    -2.77
    9
    -2.58
     soñ
    -2.56
    ：“
    -2.48
    “
    -2.44
    7
    -2.36
     basada
    -2.31
     they
    -2.30
    .”
    -2.27
    POSITIVE LOGITS
    t
    3.14
    {
    2.91
     delicada
    2.69
     fantástica
    2.39
     rígida
    2.36
    یات
    2.34
     外
    2.30
     maravilh
    2.28
     conç
    2.28
     nime
    2.27
    Activations Density 0.002%

    No Known Activations