© 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. 119653
    Prev
    Next
    INDEX
    Explanations

    titles and descriptions

    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
    Storing
    -0.07
     perpetuity
    -0.06
    Which
    -0.06
    being
    -0.06
     आईपीएस
    -0.06
     जोकि
    -0.06
     नामक
    -0.06
    Keeping
    -0.06
    gani
    -0.06
     என்ற
    -0.06
    POSITIVE LOGITS
    Aware
    0.06
    mockito
    0.06
     facture
    0.06
    ？」
    0.06
     sixteen
    0.05
    ภาษา
    0.05
     fourteen
    0.05
    のも
    0.05
    ்சை
    0.05
    냐면
    0.05
    Activations Density 0.050%

    No Known Activations