© 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. 118776
    Prev
    Next
    INDEX
    Explanations

    professional advice and guidance

    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
     Prov
    -0.06
     আঞ্চলিক
    -0.06
     regional
    -0.06
     missionary
    -0.06
     provincial
    -0.06
     интересных
    -0.06
     ভ্রমণের
    -0.06
    宠
    -0.05
     emotionally
    -0.05
     finding
    -0.05
    POSITIVE LOGITS
     in
    0.09
     the
    0.07
     have
    0.07
     has
    0.07
    ুদ্ধ
    0.06
     are
    0.06
     در
    0.06
     is
    0.06
     perspectiva
    0.06
    rumah
    0.06
    Activations Density 0.014%

    No Known Activations