© 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. 34-GEMMASCOPE-RES-131K
    7. 64419
    Prev
    Next
    INDEX
    Explanations

    system environment

    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_34/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
    挖
    -0.89
     hend
    -0.88
    arlı
    -0.86
     следует
    -0.86
    nivå
    -0.85
    Osob
    -0.85
    鴞
    -0.84
     inspirada
    -0.84
    ชีวิต
    -0.84
    OMETRY
    -0.84
    POSITIVE LOGITS
     friendly
    1.34
    friendly
    1.24
    rion
    1.19
     زیست
    1.12
    alist
    1.06
    freund
    1.06
    整備
    1.06
     Friendly
    0.99
     взя
    0.95
    Friendly
    0.93
    Activations Density 0.032%

    No Known Activations