© 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. 119200
    Prev
    Next
    INDEX
    Explanations

    rotten_bark

    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
     ikke
    -0.08
     không
    -0.08
     কিছু
    -0.07
     illetve
    -0.07
     ไม่มี
    -0.07
    ではなく
    -0.07
     cleansed
    -0.06
    郧
    -0.06
    ändert
    -0.06
    İlk
    -0.06
    POSITIVE LOGITS
     any
    0.06
     любую
    0.06
     ചെയ്
    0.06
     pemb
    0.06
     My
    0.05
    一生
    0.05
     the
    0.05
    nine
    0.05
     puissance
    0.05
    竞争
    0.05
    Activations Density 0.002%

    No Known Activations