© 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. 129049
    Prev
    Next
    INDEX
    Explanations

    federal lands, state Capitol, gun control laws

    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
     있을
    -0.06
     কিনে
    -0.06
     गाली
    -0.06
     одним
    -0.06
     Intl
    -0.06
     telefon
    -0.06
    以
    -0.06
     nightclub
    -0.06
    Rece
    -0.06
     বিশ্ববিদ্যাল
    -0.06
    POSITIVE LOGITS
    Amanda
    0.07
     agriculture
    0.06
     ፣
    0.06
     agarose
    0.06
    ?-
    0.06
     clarifications
    0.06
    环保
    0.06
     subgroup
    0.06
     satisfies
    0.06
     agricult
    0.06
    Activations Density 0.003%

    No Known Activations