© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 44493
    Prev
    Next
    INDEX
    Explanations

    special occasions and achievements

    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
     rafraî
    -2.13
     mété
    -2.08
    ть
    -2.08
    
    -2.08
    帶著
    -2.05
    阕
    -2.03
    enablog
    -2.03
    要不要
    -2.02
     précip
    -2.00
    UMES
    -1.98
    POSITIVE LOGITS
    狁
    2.58
    衎
    2.53
     заметил
    2.22
    鋮
    2.19
    𞤢
    2.19
    罨
    2.16
    ...");
    2.09
    袮
    2.08
    疍
    2.02
    siębior
    1.98
    Activations Density 0.006%

    No Known Activations