© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119874
    Prev
    Next
    INDEX
    Explanations

    you are, I feel, can get

    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
     cruel
    -1.15
    xmlns
    -1.05
     kimdir
    -1.05
     is
    -1.04
    ritos
    -1.03
     вкус
    -1.02
     
    -1.02
     Suddenly
    -1.02
    잭
    -1.00
     children
    -0.98
    POSITIVE LOGITS
    Instead
    1.29
    información
    1.29
    weren
    1.29
    geth
    1.25
     zamiast
    1.23
    zzá
    1.20
    création
    1.19
    használ
    1.16
    são
    1.16
     Rtl
    1.11
    Activations Density 0.127%

    No Known Activations