© 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. 128505
    Prev
    Next
    INDEX
    Explanations

    use of

    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
     às
    -0.07
     these
    -0.07
     ఇది
    -0.07
    ENGTH
    -0.06
     it
    -0.06
     ಇದು
    -0.06
    ленно
    -0.06
     this
    -0.06
    angered
    -0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.06
    POSITIVE LOGITS
     nicht
    0.06
     요소
    0.06
     élément
    0.06
     אחד
    0.06
     разделе
    0.06
     erv
    0.06
    յ
    0.06
    詬
    0.06
    ני
    0.06
    সম
    0.06
    Activations Density 0.011%

    No Known Activations