© 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. 118863
    Prev
    Next
    INDEX
    Explanations

    Russian leaders and names

    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
    ⁉
    -0.06
     tomorrow
    -0.06
    each
    -0.06
    However
    -0.06
    避け
    -0.06
    elimin
    -0.06
    discussed
    -0.06
    dried
    -0.06
     discussed
    -0.06
    could
    -0.06
    POSITIVE LOGITS
    불어
    0.06
    分
    0.06
    ولوژی
    0.06
    市民
    0.06
    वहीं
    0.06
    Entrepreneur
    0.06
    大规模
    0.05
     інте
    0.05
     সেখানকার
    0.05
     mesmos
    0.05
    Activations Density 0.001%

    No Known Activations