© 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. 130295
    Prev
    Next
    INDEX
    Explanations

    focus, depth of field

    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
    (%
    -0.07
     Yamaha
    -0.06
     GOVERNMENT
    -0.06
    licht
    -0.06
     progres
    -0.06
    ovir
    -0.06
    行人
    -0.06
     yamaha
    -0.05
     FORM
    -0.05
     eater
    -0.05
    POSITIVE LOGITS
     സൂ
    0.06
     metagen
    0.06
     Galilee
    0.06
    მ
    0.06
     focal
    0.06
     मोटे
    0.06
     kõ
    0.06
    जी
    0.06
     Diabetic
    0.05
     Κο
    0.05
    Activations Density 0.004%

    No Known Activations