© 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. 117163
    Prev
    Next
    INDEX
    Explanations

    It was / I have / This year

    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
     sesuai
    -0.07
     exact
    -0.07
     Ukrainian
    -0.06
     umet
    -0.06
    гато
    -0.06
    Ukrainian
    -0.06
     etat
    -0.06
     empie
    -0.06
    Segundo
    -0.06
     Each
    -0.06
    POSITIVE LOGITS
     ছিলোনা
    0.07
     ছিলনা
    0.07
     的
    0.06
    6
    0.06
    ᄌ
    0.05
    З
    0.05
    ंकडून
    0.05
    4
    0.05
     TOP
    0.05
     சீ
    0.05
    Activations Density 0.012%

    No Known Activations