© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123774
    Prev
    Next
    INDEX
    Explanations

    efficient, effective, safe, selective, automatic, simultaneous, proper, accurate, concurrent operation

    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
     a
    -2.02
     time
    -1.84
     need
    -1.66
     reviving
    -1.55
     детская
    -1.53
     advirtió
    -1.51
     habló
    -1.48
     Obtén
    -1.48
     recibió
    -1.47
     perdió
    -1.46
    POSITIVE LOGITS
     citroen
    2.05
    nemia
    1.74
     denso
    1.71
     eier
    1.63
     bruin
    1.63
     tille
    1.63
     appels
    1.60
     maske
    1.60
     ballons
    1.57
     hond
    1.56
    Activations Density 0.336%

    No Known Activations