© 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. 127376
    Prev
    Next
    INDEX
    Explanations

    play media files

    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
     to
    -1.23
     of
    -1.20
     المؤلف
    -1.16
     they
    -1.15
    似乎
    -1.13
    つけて
    -1.13
     about
    -1.11
    вав
    -1.11
    幸好
    -1.10
     ineffectual
    -1.10
    POSITIVE LOGITS
     redaktion
    1.64
    ciendo
    1.53
    播放
    1.37
    vádz
    1.32
     origines
    1.32
    瀦
    1.30
    értel
    1.28
     kämp
    1.27
    túi
    1.27
    नलोड
    1.26
    Activations Density 0.054%

    No Known Activations