© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119133
    Prev
    Next
    INDEX
    Explanations

    Duplantis, Jews, speaker, offers

    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
    দুই
    -0.07
    เยี่ยม
    -0.06
     त्यांच्या
    -0.06
     Illustrated
    -0.06
    сная
    -0.06
     scintill
    -0.05
     COLL
    -0.05
     Ref
    -0.05
     exciting
    -0.05
    Awesome
    -0.05
    POSITIVE LOGITS
     만든
    0.07
     offres
    0.07
     offer
    0.07
    offers
    0.06
     oğlu
    0.06
    Offers
    0.06
     offers
    0.06
     Save
    0.06
     overruling
    0.06
     marketed
    0.06
    Activations Density 0.005%

    No Known Activations