© 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. 119976
    Prev
    Next
    INDEX
    Explanations

    names

    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
     I
    -0.06
     luni
    -0.06
     infamous
    -0.06
     همراه
    -0.06
     Casablanca
    -0.06
     ver
    -0.06
     таке
    -0.06
     quoted
    -0.06
    সূত্র
    -0.06
    uned
    -0.05
    POSITIVE LOGITS
     není
    0.07
     अम्ब
    0.07
     குழந்தையின்
    0.07
     těchto
    0.06
     этих
    0.06
    潤
    0.06
    這些
    0.06
    ంచి
    0.06
     tehát
    0.06
     excites
    0.06
    Activations Density 0.029%

    No Known Activations