© 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. 9972
    Prev
    Next
    INDEX
    Explanations

    Can, Sal, gro, US, European, Q

    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
    这样一个
    -1.15
     usurp
    -1.07
     etiam
    -1.05
    iecie
    -1.03
     you
    -1.02
    thasone
    -1.02
     benefactor
    -1.01
     summari
    -1.00
     hinauf
    -1.00
     schließen
    -0.96
    POSITIVE LOGITS
     reflective
    1.11
     instituciones
    1.09
     consistent
    1.08
     būti
    1.05
    是多少
    1.04
     whopping
    1.03
     luz
    1.02
     miejsc
    1.02
     come
    1.02
     hacerlo
    1.02
    Activations Density 0.008%

    No Known Activations