© 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. 1712
    Prev
    Next
    INDEX
    Explanations

    http, Mr, dart, math, programming, apologies, foreign terms

    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
     (
    -1.51
    ६
    -1.49
    The
    -1.41
    如果
    -1.38
     –
    -1.37
    Everybody
    -1.36
    我们
    -1.32
    大家都
    -1.31
     метода
    -1.30
    care
    -1.28
    POSITIVE LOGITS
     it
    1.44
     oppervlak
    1.42
    dacia
    1.38
     on
    1.35
     eşofman
    1.34
     in
    1.32
    欒
    1.27
     geïsole
    1.27
     parfüm
    1.27
     saisi
    1.24
    Activations Density 0.097%

    No Known Activations