© 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. 120299
    Prev
    Next
    INDEX
    Explanations

    effect of the

    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
     কোনো
    -0.06
     گفته
    -0.06
     pendent
    -0.06
    notas
    -0.06
    資料
    -0.06
     сло
    -0.06
     އެ
    -0.06
    жли
    -0.06
     교육
    -0.05
     ምንም
    -0.05
    POSITIVE LOGITS
     their
    0.06
    ங்களிலிருந்து
    0.06
    CRUD
    0.06
     उनसे
    0.06
     compared
    0.06
     이유는
    0.06
     yaitu
    0.06
     पहुँचा
    0.06
     има
    0.05
     منهم
    0.05
    Activations Density 0.001%

    No Known Activations