© 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. 22-GEMMASCOPE-RES-131K
    7. 71773
    Prev
    Next
    INDEX
    Explanations

    past roles or contexts

    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
     месяц
    -0.86
     pamoja
    -0.85
    ኛ
    -0.85
    하는
    -0.85
    lly
    -0.84
    不能为空
    -0.84
     kwenye
    -0.82
    gn
    -0.82
     like
    -0.81
     কর
    -0.81
    POSITIVE LOGITS
     past
    1.91
     previous
    1.87
     previously
    1.63
     former
    1.63
     yester
    1.60
     originally
    1.57
    かつて
    1.53
     years
    1.52
     سابق
    1.50
    曾经
    1.47
    Activations Density 0.199%

    No Known Activations