© 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. 129523
    Prev
    Next
    INDEX
    Explanations

    another / variation

    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
     ওয়াল
    -0.06
    typen
    -0.06
    eted
    -0.06
     один
    -0.05
    astrar
    -0.05
    😁
    -0.05
     activer
    -0.05
     verwenden
    -0.05
    Always
    -0.05
     ব্যবহারে
    -0.05
    POSITIVE LOGITS
     Another
    0.08
     another
    0.07
    Another
    0.07
     അവ
    0.07
    另一
    0.07
     আরেক
    0.07
    另一种
    0.07
     outra
    0.06
    another
    0.06
     autre
    0.06
    Activations Density 0.048%

    No Known Activations