© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44737
    Prev
    Next
    INDEX
    Explanations

    Ecuador, plush, spruce, paradox

    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
    ?...
    -2.69
    ilihan
    -2.52
     cuando
    -2.48
    
    -2.47
    ࿚
    -2.41
    眥
    -2.38
     Gedanke
    -2.38
     harsh
    -2.36
    Ꝑ
    -2.36
     stumbling
    -2.33
    POSITIVE LOGITS
    er
    3.05
    to
    2.42
    {
    2.34
     ‘
    2.34
     

    2.28
    –
    2.25
    玊
    2.22
    s
    2.20
    us
    2.19
    le
    2.16
    Activations Density 0.006%

    No Known Activations