© 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. 118337
    Prev
    Next
    INDEX
    Explanations

    5

    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
     définie
    -0.08
     социа
    -0.08
     takiej
    -0.07
     også
    -0.06
     σε
    -0.06
     geniş
    -0.06
    勝利
    -0.06
     mnog
    -0.06
     вообще
    -0.06
     দেওয়া
    -0.06
    POSITIVE LOGITS
    ↵↵
    0.06
    hte
    0.06
    ore
    0.06
     (
    0.06
     ;
    0.06
     গভ
    0.05
    Lic
    0.05
    the
    0.05
     prevention
    0.05
    j
    0.05
    Activations Density 0.001%

    No Known Activations