© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118233
    Prev
    Next
    INDEX
    Explanations

    document acquisition

    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
    常に
    -0.07
     skapa
    -0.06
     في
    -0.06
     spectacular
    -0.06
    能在
    -0.06
     festive
    -0.06
    達到
    -0.06
     Holi
    -0.06
     solstice
    -0.06
    ங்குகள்
    -0.06
    POSITIVE LOGITS
    ޕ
    0.06
     etc
    0.06
     possibly
    0.06
     sampled
    0.06
     allegedly
    0.05
     каждого
    0.05
     unidentified
    0.05
    .
    0.05
     each
    0.05
     documentos
    0.05
    Activations Density 0.005%

    No Known Activations