© 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. 130355
    Prev
    Next
    INDEX
    Explanations

    Newstalk, Hudak, King, MO, lattice

    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
     Relatively
    -0.07
    Suitable
    -0.07
    suitable
    -0.07
    relatively
    -0.07
     agak
    -0.06
    ၆
    -0.06
     Öncelikle
    -0.06
     cancellations
    -0.06
     отсутствие
    -0.06
     Drapeau
    -0.06
    POSITIVE LOGITS
    them
    0.07
     the
    0.06
    </b>
    0.06
    反而
    0.06
    း
    0.06
     invece
    0.05
     எனது
    0.05
     gelijk
    0.05
    \*
    0.05
     WITHIN
    0.05
    Activations Density 0.015%

    No Known Activations