© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119963
    Prev
    Next
    INDEX
    Explanations

    from a place name

    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
     during
    -0.07
     on
    -0.07
     tijdens
    -0.06
     präsent
    -0.06
     represents
    -0.06
    Maar
    -0.06
     représente
    -0.06
     Vorstand
    -0.06
     nové
    -0.06
     Centrum
    -0.06
    POSITIVE LOGITS
     how
    0.06
    desc
    0.06
     desde
    0.06
    zeros
    0.06
    怎么
    0.06
     إليها
    0.06
    捨て
    0.05
     از
    0.05
     Corporal
    0.05
     curb
    0.05
    Activations Density 0.001%

    No Known Activations