© 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. 118070
    Prev
    Next
    INDEX
    Explanations

    fourth place or position

    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
     आर्टिफिशियल
    -0.07
     chini
    -0.07
     ताजा
    -0.06
     gallons
    -0.06
     toegang
    -0.06
     hyperlocal
    -0.06
     Cerebral
    -0.06
    姥
    -0.06
     alturas
    -0.06
     Zugang
    -0.06
    POSITIVE LOGITS
    زام
    0.06
     growth
    0.06
     tri
    0.06
     Freud
    0.06
     popular
    0.06
    楽
    0.05
     populaire
    0.05
     SR
    0.05
    featur
    0.05
     ক্রস
    0.05
    Activations Density 0.031%

    No Known Activations