© 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. 80607
    Prev
    Next
    INDEX
    Explanations

    python interpreter version

    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
     její
    -1.52
    时长
    -1.52
     mostrado
    -1.47
    ܞ
    -1.45
     múltip
    -1.45
     礼物
    -1.45
     terão
    -1.42
     "
    -1.42
    遵循
    -1.41
    沉浸
    -1.40
    POSITIVE LOGITS
    2
    2.28
    Étymologie
    1.69
     we
    1.58
    5
    1.56
     Slightly
    1.55
    ३
    1.54
     Does
    1.51
    雳
    1.49
    3
    1.49
     貼
    1.48
    Activations Density 0.007%

    No Known Activations