© 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. 130160
    Prev
    Next
    INDEX
    Explanations

    usage documentation or definition

    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
     is
    -0.06
     мои
    -0.06
    我的
    -0.06
     in
    -0.05
     என்
    -0.05
     SMALL
    -0.05
    在上
    -0.05
     नर
    -0.05
    本人
    -0.05
    dach
    -0.05
    POSITIVE LOGITS
     arguably
    0.06
     utilisant
    0.06
     médicos
    0.06
     utilizing
    0.06
     بیوی
    0.06
    ིག་
    0.06
    فتح
    0.06
     있는데
    0.06
     drugiej
    0.06
     телевиде
    0.06
    Activations Density 0.001%

    No Known Activations