© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120790
    Prev
    Next
    INDEX
    Explanations

    adjectives and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omel
    -0.06
     سخ
    -0.06
    ്ലാ
    -0.06
     PGR
    -0.05
    antlr
    -0.05
    歉
    -0.05
     dilihat
    -0.05
     antena
    -0.05
     ranged
    -0.05
                
    -0.05
    POSITIVE LOGITS
    失去
    0.06
     állapot
    0.06
     teinte
    0.06
     unemployed
    0.06
     customize
    0.06
    改造
    0.06
    Identification
    0.06
     மன
    0.06
     Erst
    0.06
     চলমান
    0.06
    Activations Density 0.003%

    No Known Activations