© 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. 10-GEMMASCOPE-RES-131K
    7. 74482
    Prev
    Next
    INDEX
    Explanations

    Polish, Russian, Ukrainian, German, Lithuanian, French, Spanish, Greek, Chinese, Tibetan words

    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
    етка
    -1.58
     după
    -1.48
    This
    -1.43
     l
    -1.41
    。
    -1.39
     gleiche
    -1.37
    LANTA
    -1.35
    utiliser
    -1.34
    われている
    -1.34
     после
    -1.33
    POSITIVE LOGITS
     οπο
    1.77
     wishes
    1.63
    虯
    1.55
     irgend
    1.55
    鹇
    1.54
     rendus
    1.52
     ་
    1.49
    ༈
    1.48
     Seleccione
    1.48
    的一些
    1.48
    Activations Density 0.044%

    No Known Activations