© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129909
    Prev
    Next
    INDEX
    Explanations

    like/others/other

    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
    page
    -0.06
     bizarre
    -0.06
     page
    -0.06
     inscr
    -0.05
     Proposals
    -0.05
    还是
    -0.05
     ALL
    -0.05
     proposals
    -0.05
    還是
    -0.05
     концу
    -0.05
    POSITIVE LOGITS
     autre
    0.07
     andere
    0.07
     پا
    0.06
    镛
    0.06
    Autres
    0.06
     तुमच्या
    0.06
    他の
    0.06
     мене
    0.06
     ل
    0.06
     другое
    0.06
    Activations Density 0.002%

    No Known Activations