© 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. 118457
    Prev
    Next
    INDEX
    Explanations

    objects and views

    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
     MA
    -0.06
     St
    -0.06
     পের
    -0.06
    ティ
    -0.06
    知名
    -0.05
    率先
    -0.05
     полноцен
    -0.05
     अतिरिक्त
    -0.05
    Chapter
    -0.05
    十四章
    -0.05
    POSITIVE LOGITS
     cible
    0.07
    Reco
    0.06
    Movies
    0.06
     proximity
    0.06
     pictogram
    0.06
    动漫
    0.06
    Hunting
    0.06
     decoy
    0.06
    quero
    0.06
     movies
    0.06
    Activations Density 0.003%

    No Known Activations