© 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. 129078
    Prev
    Next
    INDEX
    Explanations

    Q followed by auto or suspended

    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
     wrongfully
    -0.06
     NAD
    -0.06
    ื
    -0.06
     каждому
    -0.06
    ный
    -0.06
    renergic
    -0.05
     sinon
    -0.05
    णी
    -0.05
    若
    -0.05
     Höhe
    -0.05
    POSITIVE LOGITS
     внутри
    0.07
     całej
    0.07
     perder
    0.06
    怅
    0.06
    ouille
    0.06
     сообще
    0.06
     kehilangan
    0.06
     losing
    0.06
     into
    0.06
     gesamten
    0.06
    Activations Density 0.003%

    No Known Activations