© 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. 60861
    Prev
    Next
    INDEX
    Explanations

    KS abbreviation

    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
    を購入
    -2.59
    乀
    -2.52
    鷓
    -2.52
    芣
    -2.42
     ERSITY
    -2.41
    还是很
    -2.38
    𖧵
    -2.34
    頃に
    -2.31
    柃
    -2.30
     zulassen
    -2.25
    POSITIVE LOGITS
    s
    2.45
     asomb
    2.38
     Of
    2.34
     reconoc
    2.34
    vantaged
    2.30
     nightlife
    2.22
     `
    2.22
     interesante
    2.20
     notorious
    2.20
    лі
    2.19
    Activations Density 0.006%

    No Known Activations