© 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. 130144
    Prev
    Next
    INDEX
    Explanations

    list of conditions

    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
    jogador
    -0.06
    ストレ
    -0.06
     trovato
    -0.06
     Detective
    -0.06
    funny
    -0.06
     daß
    -0.05
     digunakan
    -0.05
    kath
    -0.05
    ان
    -0.05
     Samantha
    -0.05
    POSITIVE LOGITS
     মেডিকেল
    0.07
     medical
    0.06
    StoreID
    0.06
     여러분
    0.06
    >=
    0.06
     [...]
    0.06
    ئے
    0.06
    medical
    0.05
     MUI
    0.05
     Medical
    0.05
    Activations Density 0.001%

    No Known Activations