© 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. 117797
    Prev
    Next
    INDEX
    Explanations

    current time references

    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
     for
    -0.06
     has
    -0.06
     will
    -0.06
    を
    -0.06
     to
    -0.06
     must
    -0.06
     can
    -0.06
    が
    -0.06
     needs
    -0.06
    需要
    -0.06
    POSITIVE LOGITS
     the
    0.07
     questione
    0.06
     distinct
    0.06
     adopting
    0.06
     those
    0.06
     प्रोसेस
    0.06
     pillars
    0.06
    autista
    0.06
     ancora
    0.06
     İyi
    0.06
    Activations Density 0.009%

    No Known Activations