© 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. 69370
    Prev
    Next
    INDEX
    Explanations

    asking questions or defining known concepts

    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
     parfois
    -1.73
     például
    -1.64
     sudadera
    -1.60
    ных
    -1.60
     souvent
    -1.59
     gelişti
    -1.59
     取り付け
    -1.58
     裕
    -1.53
     zimowa
    -1.52
    Ⴀ
    -1.52
    POSITIVE LOGITS
     have
    1.80
    ↵↵
    1.76
     two
    1.45
     three
    1.45
     first
    1.42
     one
    1.38
     cannot
    1.35
     礼物
    1.35
     noirs
    1.33
     who
    1.31
    Activations Density 0.005%

    No Known Activations