© 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. 130041
    Prev
    Next
    INDEX
    Explanations

    most common example

    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
     sejumlah
    -1.16
    ագր
    -1.14
     algumas
    -1.13
    ことも
    -1.12
    astră
    -1.10
    bine
    -1.09
    又一次
    -1.08
    sigkeit
    -1.05
    assies
    -1.04
    ジェクト
    -1.02
    POSITIVE LOGITS
     reason
    1.13
     types
    1.02
     berlina
    1.02
     options
    0.98
     bosco
    0.96
     lanterna
    0.96
     reasons
    0.96
     zyn
    0.95
     cerim
    0.95
     teater
    0.95
    Activations Density 0.075%

    No Known Activations