© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130778
    Prev
    Next
    INDEX
    Explanations

    successes and support

    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
     هذه
    -0.08
    这也是
    -0.07
     these
    -0.07
     this
    -0.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.06
     tratado
    -0.06
    ↵↵↵↵↵↵↵↵↵↵↵
    -0.06
     Lp
    -0.06
     {}
    -0.06
    POSITIVE LOGITS
     cautiously
    0.07
    無し
    0.06
     முதலில்
    0.06
    なし
    0.06
     resourceful
    0.06
     sacks
    0.06
     bolder
    0.06
     pitiful
    0.06
     first
    0.06
     difficult
    0.06
    Activations Density 0.016%

    No Known Activations