© 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. 12854
    Prev
    Next
    INDEX
    Explanations

    whether something makes sense

    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
    ᥬ
    -1.81
     одного
    -1.69
    namientos
    -1.66
     dando
    -1.66
    ğum
    -1.59
    ₽
    -1.56
     formada
    -1.55
     diseño
    -1.54
    ࿚
    -1.53
     diseñadores
    -1.49
    POSITIVE LOGITS
    1
    1.80
    U
    1.67
     孩子
    1.66
    2
    1.62
     vespa
    1.59
    ፑ
    1.49
    ديو
    1.48
    ].
    1.48
    或
    1.48
    斯的
    1.46
    Activations Density 0.007%

    No Known Activations