© 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. 129522
    Prev
    Next
    INDEX
    Explanations

    career followed by names

    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
     zaten
    -0.07
     such
    -0.07
    Such
    -0.07
     ถนน
    -0.07
    這樣的
    -0.06
     vanaf
    -0.06
     wraz
    -0.06
     самого
    -0.06
     goal
    -0.06
     také
    -0.06
    POSITIVE LOGITS
     które
    0.06
     voordat
    0.06
     podkre
    0.06
    而后
    0.05
     sophisticated
    0.05
     Q
    0.05
    に
    0.05
    そして
    0.05
     विशेष
    0.05
    published
    0.05
    Activations Density 0.008%

    No Known Activations