© 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. 118554
    Prev
    Next
    INDEX
    Explanations

    legacy, larger, new, appropriate

    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
    ubic
    -0.06
     exclaimed
    -0.06
     पहन
    -0.06
     കരാ
    -0.05
     내부
    -0.05
     filed
    -0.05
     specifiche
    -0.05
    內部
    -0.05
    加速度
    -0.05
     internals
    -0.05
    POSITIVE LOGITS
    に適
    0.07
    适合
    0.06
     appropriate
    0.06
    legacy
    0.06
     larger
    0.06
     old
    0.06
     to
    0.06
     legacy
    0.06
     एकजुट
    0.06
     suitable
    0.06
    Activations Density 0.011%

    No Known Activations