© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 26044
    Prev
    Next
    INDEX
    Explanations

    javascript object properties

    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
     triko
    -1.38
    emptions
    -1.20
     blusas
    -1.16
    뻐
    -1.14
    Anzahl
    -1.14
    っていますが
    -1.13
     resultó
    -1.12
     inginkan
    -1.11
     alcanzó
    -1.10
    Muster
    -1.09
    POSITIVE LOGITS
     and
    1.09
    1.09
    a
    1.07
     *
    1.02
    i
    1.02
    M
    1.01
     {
    1.00
     M
    0.98
     
    0.98
    *{
    0.98
    Activations Density 0.001%

    No Known Activations