© 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. 29179
    Prev
    Next
    INDEX
    Explanations

    URL encoded strings

    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
     каждого
    -1.49
     wurde
    -1.40
     остальных
    -1.38
     trän
    -1.29
     tentu
    -1.26
     tiap
    -1.26
    ccin
    -1.25
     представителей
    -1.23
    mbor
    -1.22
     hiasan
    -1.21
    POSITIVE LOGITS
     chèvre
    1.66
     etui
    1.45
     château
    1.45
     monstru
    1.44
     vœux
    1.43
     autonomia
    1.41
     ſy
    1.41
    HAHAHAHA
    1.41
     様子
    1.39
     canale
    1.38
    Activations Density 0.027%

    No Known Activations