© 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. 116506
    Prev
    Next
    INDEX
    Explanations

    Jason Howard

    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
    它
    -0.06
    otest
    -0.06
    atuak
    -0.06
     jusqu
    -0.06
     dependence
    -0.06
     finely
    -0.06
     הפ
    -0.06
     psychological
    -0.05
     தயாரி
    -0.05
     sequels
    -0.05
    POSITIVE LOGITS
    Young
    0.07
     সাধারণ
    0.06
     voulais
    0.06
     Young
    0.06
    तीच्या
    0.06
     இளம்
    0.06
    young
    0.06
     של
    0.06
     परिचित
    0.06
     სამ
    0.06
    Activations Density 0.002%

    No Known Activations