© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 71137
    Prev
    Next
    INDEX
    Explanations

    listing enumeration elements

    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
    estaba
    -1.89
     to
    -1.86
    edere
    -1.84
     cewek
    -1.81
    comfor
    -1.76
    árbol
    -1.71
    nunca
    -1.67
     Projektu
    -1.64
    began
    -1.63
    algunos
    -1.63
    POSITIVE LOGITS
     and
    1.78
     of
    1.63
     
    1.49
    一旁的
    1.49
    </b>
    1.45
     ....
    1.34
     was
    1.32
    尚未
    1.32
     "
    1.29
    龊
    1.29
    Activations Density 0.151%

    No Known Activations