© 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. 117572
    Prev
    Next
    INDEX
    Explanations

    Annual immunisation coverage

    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
     fût
    -0.06
     rozw
    -0.06
    化した
    -0.06
     realizando
    -0.06
     exact
    -0.06
    是为了
    -0.06
     जाएंगे
    -0.06
     вами
    -0.06
     okul
    -0.06
     그래서
    -0.06
    POSITIVE LOGITS
     сред
    0.06
     spokeswoman
    0.06
    创始
    0.06
     ditu
    0.06
     semaphore
    0.06
     THIS
    0.06
    SIZ
    0.06
    FROM
    0.06
    тков
    0.06
     তরফে
    0.06
    Activations Density 0.001%

    No Known Activations